Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3520 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1149. Min Range: -4.1149
Max Act: 4.1149. Min Act: -0.1700
Data Index: 3810077 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1149. Min Range: -4.1149
Max Act: 4.0212. Min Act: -0.1700
Data Index: 3004562 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1149. Min Range: -4.1149
Max Act: 4.0212. Min Act: -0.1700
Data Index: 1179726 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.9899. Min Act: -0.1700
Data Index: 1255392 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1149. Min Range: -4.1149
Max Act: 4.0212. Min Act: -0.1700
Data Index: 4462990 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.9587. Min Act: -0.1700
Data Index: 2241285 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.9274. Min Act: -0.1700
Data Index: 8770197 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.9274. Min Act: -0.1700
Data Index: 1433689 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.9274. Min Act: -0.1700
Data Index: 5248834 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.8961. Min Act: -0.1700
Data Index: 7179489 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.8961. Min Act: -0.1700
Data Index: 2670461 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.8649. Min Act: -0.1700
Data Index: 4145356 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.8336. Min Act: -0.1700
Data Index: 6382363 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.8649. Min Act: -0.1700
Data Index: 4544210 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.8336. Min Act: -0.1700
Data Index: 1314074 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.8649. Min Act: -0.1700
Data Index: 7173437 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.8336. Min Act: -0.1700
Data Index: 684261 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.8336. Min Act: -0.1700
Data Index: 4160594 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.8336. Min Act: -0.1700
Data Index: 1854837 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1149. Min Range: -4.1149
Max Act: 3.8023. Min Act: -0.1700
Data Index: 4288393 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19