Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1922 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0109. Min Range: -7.0109
Max Act: 7.0109. Min Act: -0.1700
Data Index: 6439476 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.9797. Min Act: -0.1700
Data Index: 418108 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.8234. Min Act: -0.1700
Data Index: 4094884 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.7922. Min Act: -0.1700
Data Index: 6498365 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.7297. Min Act: -0.1700
Data Index: 5111853 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.6672. Min Act: -0.1700
Data Index: 8359461 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.6359. Min Act: -0.1700
Data Index: 2256499 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.6047. Min Act: -0.1700
Data Index: 7313330 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.6047. Min Act: -0.1700
Data Index: 1127941 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.6047. Min Act: -0.1700
Data Index: 1402814 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.5734. Min Act: -0.1700
Data Index: 885504 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.5422. Min Act: -0.1700
Data Index: 8724359 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.5734. Min Act: -0.1700
Data Index: 20261 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.5422. Min Act: -0.1700
Data Index: 113606 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.5109. Min Act: -0.1700
Data Index: 7160239 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.5422. Min Act: -0.1700
Data Index: 4525288 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.5109. Min Act: -0.1700
Data Index: 2469514 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.5109. Min Act: -0.1700
Data Index: 559155 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.5109. Min Act: -0.1700
Data Index: 6973046 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0109. Min Range: -7.0109
Max Act: 6.5109. Min Act: -0.1700
Data Index: 5785026 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19