Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 54 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.9740. Min Act: -0.1700
Data Index: 6665512 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.9115. Min Act: -0.1700
Data Index: 4027290 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.8490. Min Act: -0.1700
Data Index: 3559015 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.8490. Min Act: -0.1700
Data Index: 6522073 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.8490. Min Act: -0.1700
Data Index: 4938986 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.7865. Min Act: -0.1700
Data Index: 3091566 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.7865. Min Act: -0.1700
Data Index: 6068885 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.7240. Min Act: -0.1700
Data Index: 6248711 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.7240. Min Act: -0.1700
Data Index: 4709416 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.6615. Min Act: -0.1700
Data Index: 7576488 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.7240. Min Act: -0.1700
Data Index: 1218189 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.6615. Min Act: -0.1700
Data Index: 143761 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.5990. Min Act: -0.1700
Data Index: 2613924 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.5990. Min Act: -0.1700
Data Index: 8228398 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.4740. Min Act: -0.1700
Data Index: 1641631 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.6615. Min Act: -0.1700
Data Index: 5716985 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.5365. Min Act: -0.1700
Data Index: 4436415 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.5990. Min Act: -0.1700
Data Index: 4484260 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.5365. Min Act: -0.1700
Data Index: 1083624 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9740. Min Range: -8.9740
Max Act: 8.4740. Min Act: -0.1700
Data Index: 373600 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #19