Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1834. Min Range: -6.1834
Max Act: 6.1834. Min Act: -0.1700
Data Index: 6896402 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.9334. Min Act: -0.1700
Data Index: 4669144 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.9022. Min Act: -0.1700
Data Index: 4696265 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.9022. Min Act: -0.1700
Data Index: 7739066 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.8709. Min Act: -0.1700
Data Index: 3848874 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.7772. Min Act: -0.1700
Data Index: 5156684 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.6522. Min Act: -0.1700
Data Index: 5223384 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.5584. Min Act: -0.1700
Data Index: 8787252 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.5272. Min Act: -0.1700
Data Index: 1588268 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.5272. Min Act: -0.1700
Data Index: 1138870 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.4959. Min Act: -0.1700
Data Index: 3086462 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.4959. Min Act: -0.1700
Data Index: 841279 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.4959. Min Act: -0.1700
Data Index: 4995584 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.4959. Min Act: -0.1700
Data Index: 7956081 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.4334. Min Act: -0.1700
Data Index: 7978712 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.4022. Min Act: -0.1700
Data Index: 6604790 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.3709. Min Act: -0.1700
Data Index: 6415541 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.3709. Min Act: -0.1700
Data Index: 2534877 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.4022. Min Act: -0.1700
Data Index: 7510245 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1834. Min Range: -6.1834
Max Act: 5.4022. Min Act: -0.1700
Data Index: 2154757 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19