Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2986 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.8176. Min Act: -0.1700
Data Index: 1123187 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.4426. Min Act: -0.1700
Data Index: 7471110 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.3801. Min Act: -0.1700
Data Index: 1727671 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.3801. Min Act: -0.1700
Data Index: 387513 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.3488. Min Act: -0.1700
Data Index: 4102250 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.2551. Min Act: -0.1700
Data Index: 7801587 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.2551. Min Act: -0.1700
Data Index: 3401341 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.2551. Min Act: -0.1700
Data Index: 2172868 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.2551. Min Act: -0.1700
Data Index: 6177449 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.2551. Min Act: -0.1700
Data Index: 3168351 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.2238. Min Act: -0.1700
Data Index: 5360476 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.1926. Min Act: -0.1700
Data Index: 6885153 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.1926. Min Act: -0.1700
Data Index: 8496580 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.1926. Min Act: -0.1700
Data Index: 6624243 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.1926. Min Act: -0.1700
Data Index: 8117408 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.1926. Min Act: -0.1700
Data Index: 8392225 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.1613. Min Act: -0.1700
Data Index: 1113839 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.1613. Min Act: -0.1700
Data Index: 2403741 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.1613. Min Act: -0.1700
Data Index: 6229743 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8176. Min Range: -4.8176
Max Act: 4.1300. Min Act: -0.1700
Data Index: 2361535 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19