Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4088 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.2291. Min Range: -8.2291
Max Act: 8.2291. Min Act: -0.1700
Data Index: 6864910 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.7291. Min Act: -0.1700
Data Index: 8283257 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.6666. Min Act: -0.1700
Data Index: 4694122 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.6354. Min Act: -0.1700
Data Index: 7496566 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.5729. Min Act: -0.1700
Data Index: 3135471 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.5416. Min Act: -0.1700
Data Index: 646979 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.5416. Min Act: -0.1700
Data Index: 4688436 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.5104. Min Act: -0.1700
Data Index: 3987720 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.3541. Min Act: -0.1700
Data Index: 5467398 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.4166. Min Act: -0.1700
Data Index: 7057366 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.4166. Min Act: -0.1700
Data Index: 738040 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.3541. Min Act: -0.1700
Data Index: 3540934 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.3854. Min Act: -0.1700
Data Index: 7779057 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.3541. Min Act: -0.1700
Data Index: 6599704 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.3229. Min Act: -0.1700
Data Index: 4751054 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.3541. Min Act: -0.1700
Data Index: 1609107 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.3541. Min Act: -0.1700
Data Index: 7767020 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.3229. Min Act: -0.1700
Data Index: 1242689 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.2916. Min Act: -0.1700
Data Index: 5976400 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2291. Min Range: -8.2291
Max Act: 7.3229. Min Act: -0.1700
Data Index: 5787989 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19