Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5395 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.5731. Min Act: -0.1700
Data Index: 1464056 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.5418. Min Act: -0.1700
Data Index: 8213916 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.2293. Min Act: -0.1700
Data Index: 4540145 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.1043. Min Act: -0.1700
Data Index: 7996625 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.1043. Min Act: -0.1700
Data Index: 7863997 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.1043. Min Act: -0.1700
Data Index: 3571505 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.1043. Min Act: -0.1700
Data Index: 1121012 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.0731. Min Act: -0.1700
Data Index: 6385499 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.1043. Min Act: -0.1700
Data Index: 2913532 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.0731. Min Act: -0.1700
Data Index: 2951931 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.0106. Min Act: -0.1700
Data Index: 3583381 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.0731. Min Act: -0.1700
Data Index: 506664 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.0418. Min Act: -0.1700
Data Index: 7854769 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.0418. Min Act: -0.1700
Data Index: 7084037 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.0106. Min Act: -0.1700
Data Index: 8199583 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5731. Min Range: -7.5731
Max Act: 6.9481. Min Act: -0.1700
Data Index: 3159971 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5731. Min Range: -7.5731
Max Act: 7.0106. Min Act: -0.1700
Data Index: 1953256 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5731. Min Range: -7.5731
Max Act: 6.9793. Min Act: -0.1700
Data Index: 8615979 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5731. Min Range: -7.5731
Max Act: 6.9793. Min Act: -0.1700
Data Index: 1901133 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5731. Min Range: -7.5731
Max Act: 6.9793. Min Act: -0.1700
Data Index: 557990 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19