Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1304 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3938. Min Range: -6.3938
Max Act: 6.3938. Min Act: -0.1700
Data Index: 2445782 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3938. Min Range: -6.3938
Max Act: 6.1126. Min Act: -0.1700
Data Index: 4711781 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3938. Min Range: -6.3938
Max Act: 6.0501. Min Act: -0.1700
Data Index: 3954650 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.9251. Min Act: -0.1700
Data Index: 7335266 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.8938. Min Act: -0.1700
Data Index: 6827426 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.8626. Min Act: -0.1700
Data Index: 4080137 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.8938. Min Act: -0.1700
Data Index: 7807520 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.8626. Min Act: -0.1700
Data Index: 8668550 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.8001. Min Act: -0.1700
Data Index: 4226432 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.8313. Min Act: -0.1700
Data Index: 1455265 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.8001. Min Act: -0.1700
Data Index: 3468505 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.8313. Min Act: -0.1700
Data Index: 2616395 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.7688. Min Act: -0.1700
Data Index: 67824 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.7688. Min Act: -0.1700
Data Index: 448598 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.7688. Min Act: -0.1700
Data Index: 3785887 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.7376. Min Act: -0.1700
Data Index: 47281 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.7376. Min Act: -0.1700
Data Index: 175769 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.7376. Min Act: -0.1700
Data Index: 8648828 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.7688. Min Act: -0.1700
Data Index: 2756246 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3938. Min Range: -6.3938
Max Act: 5.7063. Min Act: -0.1700
Data Index: 5595146 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19