Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 668 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.5302. Min Act: -0.1700
Data Index: 5121855 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.4364. Min Act: -0.1700
Data Index: 6807734 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.3739. Min Act: -0.1700
Data Index: 4150901 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.3426. Min Act: -0.1700
Data Index: 5699309 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2801. Min Act: -0.1700
Data Index: 3914483 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2489. Min Act: -0.1700
Data Index: 4454207 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.3114. Min Act: -0.1700
Data Index: 5048269 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2801. Min Act: -0.1700
Data Index: 532766 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.3114. Min Act: -0.1700
Data Index: 7336156 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2176. Min Act: -0.1700
Data Index: 5382406 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2176. Min Act: -0.1700
Data Index: 8677838 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2176. Min Act: -0.1700
Data Index: 3346302 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2176. Min Act: -0.1700
Data Index: 3464130 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2176. Min Act: -0.1700
Data Index: 1664584 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2176. Min Act: -0.1700
Data Index: 7385936 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2176. Min Act: -0.1700
Data Index: 2131247 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2176. Min Act: -0.1700
Data Index: 6976147 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2176. Min Act: -0.1700
Data Index: 6336426 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.2176. Min Act: -0.1700
Data Index: 6627651 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5302. Min Range: -4.5302
Max Act: 4.1551. Min Act: -0.1700
Data Index: 2611455 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19