Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1925 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.3988. Min Range: -5.3988
Max Act: 5.3988. Min Act: -0.1700
Data Index: 841102 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.9926. Min Act: -0.1700
Data Index: 1816089 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.9301. Min Act: -0.1700
Data Index: 1011336 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.8988. Min Act: -0.1700
Data Index: 2811618 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.8988. Min Act: -0.1700
Data Index: 2829834 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.8363. Min Act: -0.1700
Data Index: 3133239 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.8676. Min Act: -0.1700
Data Index: 5576098 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.8363. Min Act: -0.1700
Data Index: 4200453 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.8676. Min Act: -0.1700
Data Index: 2874055 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.8363. Min Act: -0.1700
Data Index: 61575 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.8676. Min Act: -0.1700
Data Index: 3136741 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.8051. Min Act: -0.1700
Data Index: 3136771 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.7738. Min Act: -0.1700
Data Index: 2829835 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.7738. Min Act: -0.1700
Data Index: 1606850 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.7738. Min Act: -0.1700
Data Index: 2806696 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.7738. Min Act: -0.1700
Data Index: 2668882 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.7738. Min Act: -0.1700
Data Index: 7863346 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.7738. Min Act: -0.1700
Data Index: 141314 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.7426. Min Act: -0.1700
Data Index: 4079561 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3988. Min Range: -5.3988
Max Act: 4.7426. Min Act: -0.1700
Data Index: 6371281 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19