Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3756 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.9369. Min Act: -0.1700
Data Index: 5526519 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.9057. Min Act: -0.1700
Data Index: 7512711 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.8744. Min Act: -0.1700
Data Index: 7220804 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.7807. Min Act: -0.1700
Data Index: 1542925 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.6869. Min Act: -0.1700
Data Index: 4542499 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.6869. Min Act: -0.1700
Data Index: 6313647 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.6244. Min Act: -0.1700
Data Index: 434579 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.5932. Min Act: -0.1700
Data Index: 1802354 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.5619. Min Act: -0.1700
Data Index: 8357806 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.5619. Min Act: -0.1700
Data Index: 5039348 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.5619. Min Act: -0.1700
Data Index: 620159 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.5619. Min Act: -0.1700
Data Index: 8131347 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.5307. Min Act: -0.1700
Data Index: 1156806 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.5619. Min Act: -0.1700
Data Index: 8297705 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.5619. Min Act: -0.1700
Data Index: 1781024 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.5619. Min Act: -0.1700
Data Index: 3214245 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.5307. Min Act: -0.1700
Data Index: 5286918 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.5307. Min Act: -0.1700
Data Index: 6290604 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.5619. Min Act: -0.1700
Data Index: 5097350 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9369. Min Range: -4.9369
Max Act: 4.4994. Min Act: -0.1700
Data Index: 4061620 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19