Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3299 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.2939. Min Act: -0.1700
Data Index: 4427820 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.2626. Min Act: -0.1700
Data Index: 6999814 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.2314. Min Act: -0.1700
Data Index: 2335541 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.2001. Min Act: -0.1700
Data Index: 2335538 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.2001. Min Act: -0.1700
Data Index: 4765322 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.2001. Min Act: -0.1700
Data Index: 2563273 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.2001. Min Act: -0.1700
Data Index: 3055119 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.1689. Min Act: -0.1700
Data Index: 2335553 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.1376. Min Act: -0.1700
Data Index: 4353737 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.1376. Min Act: -0.1700
Data Index: 2335537 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.1376. Min Act: -0.1700
Data Index: 2335547 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.1376. Min Act: -0.1700
Data Index: 8606338 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.1376. Min Act: -0.1700
Data Index: 6192682 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.1689. Min Act: -0.1700
Data Index: 2335532 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.1376. Min Act: -0.1700
Data Index: 2335546 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.1064. Min Act: -0.1700
Data Index: 3533428 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.1064. Min Act: -0.1700
Data Index: 7817298 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.0751. Min Act: -0.1700
Data Index: 2419395 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.0751. Min Act: -0.1700
Data Index: 3086933 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2939. Min Range: -4.2939
Max Act: 4.0751. Min Act: -0.1700
Data Index: 152008 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19