Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3026 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0142. Min Range: -6.0142
Max Act: 6.0142. Min Act: -0.1700
Data Index: 3650628 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.8892. Min Act: -0.1700
Data Index: 6652468 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.8892. Min Act: -0.1700
Data Index: 910292 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.7017. Min Act: -0.1700
Data Index: 7753536 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.6392. Min Act: -0.1700
Data Index: 5423960 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.6080. Min Act: -0.1700
Data Index: 4262117 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.5767. Min Act: -0.1700
Data Index: 2477958 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.5767. Min Act: -0.1700
Data Index: 3789169 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.5455. Min Act: -0.1700
Data Index: 3785729 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.5455. Min Act: -0.1700
Data Index: 8530697 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.5142. Min Act: -0.1700
Data Index: 2601628 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.5142. Min Act: -0.1700
Data Index: 8573158 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.4517. Min Act: -0.1700
Data Index: 108656 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.4205. Min Act: -0.1700
Data Index: 2461757 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.4517. Min Act: -0.1700
Data Index: 476451 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.4517. Min Act: -0.1700
Data Index: 2125674 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.4205. Min Act: -0.1700
Data Index: 4045312 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.4517. Min Act: -0.1700
Data Index: 3945946 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.4205. Min Act: -0.1700
Data Index: 4172163 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0142. Min Range: -6.0142
Max Act: 5.4205. Min Act: -0.1700
Data Index: 7071625 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19