Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0295. Min Range: -4.0295
Max Act: 4.0295. Min Act: -0.1700
Data Index: 6830961 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0295. Min Range: -4.0295
Max Act: 4.0295. Min Act: -0.1700
Data Index: 6992607 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.9982. Min Act: -0.1700
Data Index: 689262 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.9357. Min Act: -0.1700
Data Index: 5549758 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.9357. Min Act: -0.1700
Data Index: 5999148 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.9044. Min Act: -0.1700
Data Index: 8026937 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.9357. Min Act: -0.1700
Data Index: 6917207 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.9357. Min Act: -0.1700
Data Index: 7404011 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.8732. Min Act: -0.1700
Data Index: 3486161 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.9044. Min Act: -0.1700
Data Index: 461164 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.8732. Min Act: -0.1700
Data Index: 230229 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.8732. Min Act: -0.1700
Data Index: 3522907 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.8732. Min Act: -0.1700
Data Index: 3581100 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.8732. Min Act: -0.1700
Data Index: 7827375 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.8419. Min Act: -0.1700
Data Index: 4965209 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.8419. Min Act: -0.1700
Data Index: 4965202 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.8419. Min Act: -0.1700
Data Index: 3963663 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.8419. Min Act: -0.1700
Data Index: 7423980 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.8419. Min Act: -0.1700
Data Index: 2165052 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0295. Min Range: -4.0295
Max Act: 3.8106. Min Act: -0.1700
Data Index: 1716572 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19