Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 294 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.2147. Min Act: -0.1700
Data Index: 4450691 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.2147. Min Act: -0.1700
Data Index: 3313181 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.1834. Min Act: -0.1700
Data Index: 3248000 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.1522. Min Act: -0.1700
Data Index: 6779997 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.1209. Min Act: -0.1700
Data Index: 8365295 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.1209. Min Act: -0.1700
Data Index: 4955824 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.1209. Min Act: -0.1700
Data Index: 3170289 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.1209. Min Act: -0.1700
Data Index: 2133275 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.0584. Min Act: -0.1700
Data Index: 3564315 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.0897. Min Act: -0.1700
Data Index: 1250079 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.0272. Min Act: -0.1700
Data Index: 3012946 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.0272. Min Act: -0.1700
Data Index: 3513929 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9959. Min Act: -0.1699
Data Index: 3498004 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9959. Min Act: -0.1700
Data Index: 405770 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9959. Min Act: -0.1700
Data Index: 1127194 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2147. Min Range: -6.2147
Max Act: 6.0272. Min Act: -0.1700
Data Index: 2487831 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9959. Min Act: -0.1700
Data Index: 6462188 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9959. Min Act: -0.1700
Data Index: 4676008 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9959. Min Act: -0.1700
Data Index: 3902942 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2147. Min Range: -6.2147
Max Act: 5.9647. Min Act: -0.1700
Data Index: 3824365 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #19