Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2554 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 13.2023. Min Range: -13.2023
Max Act: 13.2023. Min Act: -0.1700
Data Index: 209084 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.2023. Min Range: -13.2023
Max Act: 12.7648. Min Act: -0.1700
Data Index: 2773104 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.2023. Min Range: -13.2023
Max Act: 12.5148. Min Act: -0.1700
Data Index: 670078 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.2023. Min Range: -13.2023
Max Act: 12.4523. Min Act: -0.1700
Data Index: 620821 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.2023. Min Range: -13.2023
Max Act: 12.2023. Min Act: -0.1700
Data Index: 252277 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.2023. Min Range: -13.2023
Max Act: 12.2023. Min Act: -0.1700
Data Index: 3309888 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.2023. Min Range: -13.2023
Max Act: 12.2023. Min Act: -0.1700
Data Index: 2237744 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.2023. Min Range: -13.2023
Max Act: 12.0773. Min Act: -0.1700
Data Index: 5663715 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.2023. Min Range: -13.2023
Max Act: 12.0773. Min Act: -0.1700
Data Index: 4515438 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.2023. Min Range: -13.2023
Max Act: 12.0773. Min Act: -0.1700
Data Index: 6423836 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.2023. Min Range: -13.2023
Max Act: 11.9523. Min Act: -0.1700
Data Index: 6855048 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.2023. Min Range: -13.2023
Max Act: 11.9523. Min Act: -0.1700
Data Index: 8351355 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.2023. Min Range: -13.2023
Max Act: 11.8273. Min Act: -0.1700
Data Index: 8726413 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.2023. Min Range: -13.2023
Max Act: 11.8273. Min Act: -0.1700
Data Index: 6016176 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.2023. Min Range: -13.2023
Max Act: 11.8273. Min Act: -0.1700
Data Index: 3969536 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.2023. Min Range: -13.2023
Max Act: 11.7023. Min Act: -0.1700
Data Index: 6265253 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.2023. Min Range: -13.2023
Max Act: 11.6398. Min Act: -0.1700
Data Index: 1265732 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.2023. Min Range: -13.2023
Max Act: 11.6398. Min Act: -0.1700
Data Index: 6322166 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.2023. Min Range: -13.2023
Max Act: 11.7023. Min Act: -0.1700
Data Index: 6847610 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.2023. Min Range: -13.2023
Max Act: 11.6398. Min Act: -0.1700
Data Index: 4075059 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #19