Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.6791. Min Act: -0.1700
Data Index: 5819754 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.5541. Min Act: -0.1700
Data Index: 1668023 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.3979. Min Act: -0.1700
Data Index: 6997967 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.3979. Min Act: -0.1700
Data Index: 2977034 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.3666. Min Act: -0.1700
Data Index: 419988 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.3354. Min Act: -0.1700
Data Index: 3672629 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.3041. Min Act: -0.1700
Data Index: 5196405 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.3041. Min Act: -0.1700
Data Index: 2908745 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.2729. Min Act: -0.1700
Data Index: 2243923 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.2729. Min Act: -0.1700
Data Index: 5336407 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.2729. Min Act: -0.1700
Data Index: 749821 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.2416. Min Act: -0.1700
Data Index: 1655318 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.2416. Min Act: -0.1700
Data Index: 2429190 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.2416. Min Act: -0.1700
Data Index: 8769862 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.2104. Min Act: -0.1700
Data Index: 642004 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.2104. Min Act: -0.1700
Data Index: 4636622 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.1791. Min Act: -0.1700
Data Index: 1237283 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.1791. Min Act: -0.1700
Data Index: 6386940 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.1791. Min Act: -0.1700
Data Index: 3058575 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6791. Min Range: -4.6791
Max Act: 4.1479. Min Act: -0.1700
Data Index: 324847 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19