Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3507 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.7441. Min Act: -0.1700
Data Index: 622016 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.7129. Min Act: -0.1700
Data Index: 145232 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.5254. Min Act: -0.1700
Data Index: 1321910 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.4941. Min Act: -0.1700
Data Index: 812473 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.4316. Min Act: -0.1700
Data Index: 7238682 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.4316. Min Act: -0.1700
Data Index: 1224556 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.3379. Min Act: -0.1700
Data Index: 5280711 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.3379. Min Act: -0.1700
Data Index: 7930665 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.3066. Min Act: -0.1700
Data Index: 1095097 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.2754. Min Act: -0.1700
Data Index: 5647350 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.2441. Min Act: -0.1700
Data Index: 3960555 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.2129. Min Act: -0.1700
Data Index: 4005287 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.1816. Min Act: -0.1700
Data Index: 2677375 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.2129. Min Act: -0.1700
Data Index: 5968720 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.1191. Min Act: -0.1700
Data Index: 3533668 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.1504. Min Act: -0.1700
Data Index: 4416593 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.1191. Min Act: -0.1700
Data Index: 228063 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.1191. Min Act: -0.1700
Data Index: 154042 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.1191. Min Act: -0.1700
Data Index: 6695167 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7441. Min Range: -5.7441
Max Act: 5.0879. Min Act: -0.1700
Data Index: 184699 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19