Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1198 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.7253. Min Act: -0.1700
Data Index: 6717072 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.6628. Min Act: -0.1700
Data Index: 1607410 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.6316. Min Act: -0.1700
Data Index: 8726714 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.5066. Min Act: -0.1700
Data Index: 5079202 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.4128. Min Act: -0.1700
Data Index: 8832392 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.4128. Min Act: -0.1700
Data Index: 1825941 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2878. Min Act: -0.1700
Data Index: 5643011 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.3191. Min Act: -0.1700
Data Index: 1283108 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2878. Min Act: -0.1700
Data Index: 1825942 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2878. Min Act: -0.1700
Data Index: 8284266 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2878. Min Act: -0.1700
Data Index: 746916 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2878. Min Act: -0.1700
Data Index: 2211268 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2566. Min Act: -0.1700
Data Index: 7460672 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2253. Min Act: -0.1700
Data Index: 5289086 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2253. Min Act: -0.1700
Data Index: 960408 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2253. Min Act: -0.1700
Data Index: 1576206 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2253. Min Act: -0.1700
Data Index: 3702381 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.2253. Min Act: -0.1700
Data Index: 2481855 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.1941. Min Act: -0.1700
Data Index: 4447484 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7253. Min Range: -4.7253
Max Act: 4.1628. Min Act: -0.1700
Data Index: 7317507 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #19