Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3966 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.4176. Min Act: -0.1700
Data Index: 7828418 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.2921. Min Act: -0.1700
Data Index: 6314715 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.2450. Min Act: -0.1700
Data Index: 1465314 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.2136. Min Act: -0.1700
Data Index: 3924444 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.1978. Min Act: -0.1700
Data Index: 2798559 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.1821. Min Act: -0.1700
Data Index: 6572238 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.1506. Min Act: -0.1700
Data Index: 4021699 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.1664. Min Act: -0.1700
Data Index: 2128771 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.1034. Min Act: -0.1700
Data Index: 2551328 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.1349. Min Act: -0.1700
Data Index: 8712403 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.0876. Min Act: -0.1700
Data Index: 1313278 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.1191. Min Act: -0.1700
Data Index: 5899351 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.0876. Min Act: -0.1700
Data Index: 5976049 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.1191. Min Act: -0.1700
Data Index: 6857940 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.0876. Min Act: -0.1700
Data Index: 1579371 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.0245. Min Act: -0.1700
Data Index: 1531396 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.0403. Min Act: -0.1700
Data Index: 7880348 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.0561. Min Act: -0.1700
Data Index: 4108273 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.0245. Min Act: -0.1700
Data Index: 7755752 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4176. Min Range: -3.4176
Max Act: 3.0403. Min Act: -0.1700
Data Index: 1668496 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19