Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1644 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.5229. Min Act: -0.1700
Data Index: 8686455 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.4916. Min Act: -0.1700
Data Index: 5653709 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.5385. Min Act: -0.1700
Data Index: 997459 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.5229. Min Act: -0.1700
Data Index: 2298554 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.4759. Min Act: -0.1700
Data Index: 6894309 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.4446. Min Act: -0.1700
Data Index: 8261998 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.4602. Min Act: -0.1700
Data Index: 5338967 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.4446. Min Act: -0.1700
Data Index: 5167212 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.4446. Min Act: -0.1700
Data Index: 6368694 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.4446. Min Act: -0.1700
Data Index: 2143512 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.4759. Min Act: -0.1700
Data Index: 5967092 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.4289. Min Act: -0.1700
Data Index: 8233688 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.3975. Min Act: -0.1700
Data Index: 7125503 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.4132. Min Act: -0.1700
Data Index: 4817447 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.4132. Min Act: -0.1700
Data Index: 2120035 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.3975. Min Act: -0.1700
Data Index: 665259 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.3975. Min Act: -0.1700
Data Index: 3951882 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.3505. Min Act: -0.1700
Data Index: 439530 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.3818. Min Act: -0.1700
Data Index: 6827876 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5385. Min Range: -3.5385
Max Act: 3.3662. Min Act: -0.1700
Data Index: 64223 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19