Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3641 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0541. Min Range: -6.0541
Max Act: 6.0541. Min Act: -0.1700
Data Index: 775250 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.8666. Min Act: -0.1700
Data Index: 470142 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.8354. Min Act: -0.1700
Data Index: 5452504 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.8354. Min Act: -0.1700
Data Index: 1915088 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.8354. Min Act: -0.1700
Data Index: 8203232 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.8041. Min Act: -0.1700
Data Index: 8118214 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.8041. Min Act: -0.1700
Data Index: 1165846 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.8041. Min Act: -0.1700
Data Index: 5605922 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.7416. Min Act: -0.1700
Data Index: 6053053 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.7416. Min Act: -0.1700
Data Index: 2063412 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.7104. Min Act: -0.1700
Data Index: 8609022 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.7104. Min Act: -0.1700
Data Index: 209147 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.6791. Min Act: -0.1700
Data Index: 8504959 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.7104. Min Act: -0.1700
Data Index: 5149407 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.6791. Min Act: -0.1700
Data Index: 860594 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.6479. Min Act: -0.1700
Data Index: 7486945 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.6791. Min Act: -0.1700
Data Index: 8356987 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.6791. Min Act: -0.1700
Data Index: 829384 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.6791. Min Act: -0.1700
Data Index: 6889855 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0541. Min Range: -6.0541
Max Act: 5.6791. Min Act: -0.1700
Data Index: 6100365 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19