Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3954 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2832. Min Range: -6.2832
Max Act: 6.2832. Min Act: -0.1700
Data Index: 5880305 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2832. Min Range: -6.2832
Max Act: 6.0020. Min Act: -0.1700
Data Index: 954872 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.9707. Min Act: -0.1700
Data Index: 382969 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.9082. Min Act: -0.1700
Data Index: 6414760 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.9082. Min Act: -0.1700
Data Index: 6928720 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.9082. Min Act: -0.1700
Data Index: 874120 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.9082. Min Act: -0.1700
Data Index: 1470922 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.8770. Min Act: -0.1700
Data Index: 3797411 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.8145. Min Act: -0.1700
Data Index: 6055100 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.8145. Min Act: -0.1700
Data Index: 837916 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.8145. Min Act: -0.1700
Data Index: 3791582 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.8145. Min Act: -0.1700
Data Index: 3725291 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.8145. Min Act: -0.1700
Data Index: 2465833 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.7832. Min Act: -0.1700
Data Index: 1669512 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.7832. Min Act: -0.1700
Data Index: 1656828 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.7832. Min Act: -0.1700
Data Index: 2626651 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.7520. Min Act: -0.1700
Data Index: 6286377 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.7520. Min Act: -0.1700
Data Index: 5246859 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.7520. Min Act: -0.1700
Data Index: 6895185 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2832. Min Range: -6.2832
Max Act: 5.7207. Min Act: -0.1700
Data Index: 3226110 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19