Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1465. Min Range: -5.1465
Max Act: 5.1465. Min Act: -0.1700
Data Index: 5875993 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1465. Min Range: -5.1465
Max Act: 5.0840. Min Act: -0.1700
Data Index: 3007234 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9902. Min Act: -0.1700
Data Index: 320053 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.9277. Min Act: -0.1700
Data Index: 1179822 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.8965. Min Act: -0.1700
Data Index: 5548046 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.7715. Min Act: -0.1700
Data Index: 7174206 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.7090. Min Act: -0.1700
Data Index: 294941 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.7090. Min Act: -0.1700
Data Index: 3034677 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.7090. Min Act: -0.1700
Data Index: 58356 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.6777. Min Act: -0.1700
Data Index: 2332638 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.6777. Min Act: -0.1700
Data Index: 7158277 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.6152. Min Act: -0.1700
Data Index: 3779704 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.5840. Min Act: -0.1700
Data Index: 6789221 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.5840. Min Act: -0.1700
Data Index: 7179715 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.5527. Min Act: -0.1700
Data Index: 4548680 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.5215. Min Act: -0.1700
Data Index: 6700023 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.5527. Min Act: -0.1700
Data Index: 7025068 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.5527. Min Act: -0.1700
Data Index: 4472612 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.4902. Min Act: -0.1700
Data Index: 697864 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1465. Min Range: -5.1465
Max Act: 4.4902. Min Act: -0.1700
Data Index: 480346 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19