Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3765 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.4652. Min Act: -0.1700
Data Index: 4726497 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.4340. Min Act: -0.1700
Data Index: 4927733 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.4027. Min Act: -0.1700
Data Index: 6046262 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.4340. Min Act: -0.1700
Data Index: 2221904 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.4027. Min Act: -0.1700
Data Index: 5096255 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.4027. Min Act: -0.1700
Data Index: 1650546 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.3714. Min Act: -0.1700
Data Index: 5855743 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.3402. Min Act: -0.1700
Data Index: 7521647 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.3402. Min Act: -0.1700
Data Index: 2518385 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.3714. Min Act: -0.1700
Data Index: 126117 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.3402. Min Act: -0.1700
Data Index: 2040870 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.3402. Min Act: -0.1700
Data Index: 8285287 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.3089. Min Act: -0.1700
Data Index: 6557967 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.3089. Min Act: -0.1700
Data Index: 3756003 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.2777. Min Act: -0.1700
Data Index: 4891119 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.3089. Min Act: -0.1700
Data Index: 2950856 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.3089. Min Act: -0.1700
Data Index: 6439712 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.2777. Min Act: -0.1700
Data Index: 2726275 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.3089. Min Act: -0.1700
Data Index: 4435966 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4652. Min Range: -4.4652
Max Act: 4.2777. Min Act: -0.1700
Data Index: 4011982 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #19