Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2554 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5152. Min Range: -6.5152
Max Act: 6.5152. Min Act: -0.1700
Data Index: 6732874 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5152. Min Range: -6.5152
Max Act: 6.0152. Min Act: -0.1700
Data Index: 550382 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.9840. Min Act: -0.1700
Data Index: 6285382 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5152. Min Range: -6.5152
Max Act: 6.0152. Min Act: -0.1700
Data Index: 1561275 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.9527. Min Act: -0.1700
Data Index: 7970984 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.9215. Min Act: -0.1700
Data Index: 2003822 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.9215. Min Act: -0.1700
Data Index: 3579656 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.8902. Min Act: -0.1700
Data Index: 5772237 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.8590. Min Act: -0.1700
Data Index: 4886921 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.8902. Min Act: -0.1700
Data Index: 5325135 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.8590. Min Act: -0.1700
Data Index: 1332381 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.8277. Min Act: -0.1700
Data Index: 8670784 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.8277. Min Act: -0.1700
Data Index: 5422812 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.8277. Min Act: -0.1700
Data Index: 948110 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.7965. Min Act: -0.1700
Data Index: 7842126 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.7965. Min Act: -0.1700
Data Index: 6403385 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.7965. Min Act: -0.1700
Data Index: 2102941 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.7652. Min Act: -0.1700
Data Index: 2454182 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.7340. Min Act: -0.1700
Data Index: 749650 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5152. Min Range: -6.5152
Max Act: 5.7652. Min Act: -0.1700
Data Index: 6487242 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19