Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4932. Min Range: -9.4932
Max Act: 9.4932. Min Act: -0.1700
Data Index: 300960 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4932. Min Range: -9.4932
Max Act: 9.0557. Min Act: -0.1700
Data Index: 6607948 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.9307. Min Act: -0.1700
Data Index: 7197094 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.8682. Min Act: -0.1700
Data Index: 5410641 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.8682. Min Act: -0.1700
Data Index: 2691746 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.7432. Min Act: -0.1700
Data Index: 1284709 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.6807. Min Act: -0.1700
Data Index: 4500763 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.6182. Min Act: -0.1700
Data Index: 7235779 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.6182. Min Act: -0.1700
Data Index: 7823589 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.6182. Min Act: -0.1700
Data Index: 1844159 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.5557. Min Act: -0.1700
Data Index: 1898891 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.5557. Min Act: -0.1700
Data Index: 1101807 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.4307. Min Act: -0.1700
Data Index: 3641157 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.4307. Min Act: -0.1700
Data Index: 8016420 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.4307. Min Act: -0.1700
Data Index: 2251449 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.4307. Min Act: -0.1700
Data Index: 2460211 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.4307. Min Act: -0.1700
Data Index: 7497025 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.4307. Min Act: -0.1700
Data Index: 4413523 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.4307. Min Act: -0.1700
Data Index: 2721643 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4932. Min Range: -9.4932
Max Act: 8.4307. Min Act: -0.1700
Data Index: 44782 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #19