Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.7830. Min Act: -0.1700
Data Index: 2834647 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.5018. Min Act: -0.1700
Data Index: 5474146 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.5018. Min Act: -0.1700
Data Index: 7683956 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.3455. Min Act: -0.1700
Data Index: 1415423 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.3143. Min Act: -0.1700
Data Index: 4884381 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.2205. Min Act: -0.1700
Data Index: 6190979 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.2205. Min Act: -0.1700
Data Index: 4186990 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.1893. Min Act: -0.1700
Data Index: 1522243 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.1893. Min Act: -0.1700
Data Index: 2714649 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.1893. Min Act: -0.1700
Data Index: 1059615 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.1580. Min Act: -0.1700
Data Index: 7853394 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.1580. Min Act: -0.1700
Data Index: 3582196 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.1268. Min Act: -0.1700
Data Index: 2637233 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.1268. Min Act: -0.1700
Data Index: 6967689 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.0955. Min Act: -0.1700
Data Index: 6409128 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.0955. Min Act: -0.1700
Data Index: 430052 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.0955. Min Act: -0.1700
Data Index: 4397422 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.0643. Min Act: -0.1700
Data Index: 2325744 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.0018. Min Act: -0.1700
Data Index: 2325759 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7830. Min Range: -7.7830
Max Act: 7.0330. Min Act: -0.1700
Data Index: 3943384 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19