Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1853 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.7192. Min Act: -0.1700
Data Index: 5276551 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.7192. Min Act: -0.1700
Data Index: 1436618 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.6567. Min Act: -0.1700
Data Index: 1161524 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.4692. Min Act: -0.1700
Data Index: 4752592 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.4380. Min Act: -0.1700
Data Index: 5499767 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.3442. Min Act: -0.1700
Data Index: 8145323 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.3442. Min Act: -0.1700
Data Index: 3577063 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.2817. Min Act: -0.1700
Data Index: 3102272 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.3130. Min Act: -0.1700
Data Index: 1193250 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.3130. Min Act: -0.1700
Data Index: 6858753 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.3130. Min Act: -0.1700
Data Index: 8304589 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.2817. Min Act: -0.1700
Data Index: 770364 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.3130. Min Act: -0.1700
Data Index: 6832706 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.2817. Min Act: -0.1700
Data Index: 1195762 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.2817. Min Act: -0.1700
Data Index: 3262675 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.3130. Min Act: -0.1700
Data Index: 4239668 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.2505. Min Act: -0.1700
Data Index: 435375 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.2505. Min Act: -0.1700
Data Index: 1583778 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.2505. Min Act: -0.1700
Data Index: 4381659 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7192. Min Range: -6.7192
Max Act: 6.2192. Min Act: -0.1700
Data Index: 742086 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #19