Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3113 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3386. Min Range: -6.3386
Max Act: 6.3386. Min Act: -0.1700
Data Index: 3724145 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3386. Min Range: -6.3386
Max Act: 6.2136. Min Act: -0.1700
Data Index: 1543756 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3386. Min Range: -6.3386
Max Act: 6.1198. Min Act: -0.1700
Data Index: 2984780 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3386. Min Range: -6.3386
Max Act: 6.0886. Min Act: -0.1700
Data Index: 3941892 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3386. Min Range: -6.3386
Max Act: 6.0261. Min Act: -0.1700
Data Index: 7053678 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3386. Min Range: -6.3386
Max Act: 6.0261. Min Act: -0.1700
Data Index: 7871238 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3386. Min Range: -6.3386
Max Act: 6.0261. Min Act: -0.1700
Data Index: 1300526 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3386. Min Range: -6.3386
Max Act: 6.0261. Min Act: -0.1700
Data Index: 8809537 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3386. Min Range: -6.3386
Max Act: 5.9323. Min Act: -0.1700
Data Index: 8440944 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3386. Min Range: -6.3386
Max Act: 5.9323. Min Act: -0.1700
Data Index: 1066842 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3386. Min Range: -6.3386
Max Act: 5.9323. Min Act: -0.1700
Data Index: 6385048 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3386. Min Range: -6.3386
Max Act: 5.9323. Min Act: -0.1700
Data Index: 8281803 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3386. Min Range: -6.3386
Max Act: 5.9011. Min Act: -0.1700
Data Index: 7847180 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3386. Min Range: -6.3386
Max Act: 5.9011. Min Act: -0.1700
Data Index: 1665814 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3386. Min Range: -6.3386
Max Act: 5.9011. Min Act: -0.1700
Data Index: 3433481 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3386. Min Range: -6.3386
Max Act: 5.9011. Min Act: -0.1700
Data Index: 7759058 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3386. Min Range: -6.3386
Max Act: 5.9011. Min Act: -0.1700
Data Index: 8051516 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3386. Min Range: -6.3386
Max Act: 5.8698. Min Act: -0.1700
Data Index: 3905555 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3386. Min Range: -6.3386
Max Act: 5.9011. Min Act: -0.1700
Data Index: 7902587 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3386. Min Range: -6.3386
Max Act: 5.8698. Min Act: -0.1700
Data Index: 4606831 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19