Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1536 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1859. Min Range: -5.1859
Max Act: 5.1547. Min Act: -0.1700
Data Index: 5292879 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1859. Min Range: -5.1859
Max Act: 5.1859. Min Act: -0.1700
Data Index: 258571 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1859. Min Range: -5.1859
Max Act: 5.1547. Min Act: -0.1700
Data Index: 4669277 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1859. Min Range: -5.1859
Max Act: 5.1234. Min Act: -0.1700
Data Index: 8548945 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1859. Min Range: -5.1859
Max Act: 5.1234. Min Act: -0.1700
Data Index: 8309383 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1859. Min Range: -5.1859
Max Act: 5.0609. Min Act: -0.1700
Data Index: 2939035 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1859. Min Range: -5.1859
Max Act: 5.0297. Min Act: -0.1700
Data Index: 5293987 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1859. Min Range: -5.1859
Max Act: 4.9984. Min Act: -0.1700
Data Index: 4755390 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1859. Min Range: -5.1859
Max Act: 4.9984. Min Act: -0.1700
Data Index: 1373514 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1859. Min Range: -5.1859
Max Act: 5.0297. Min Act: -0.1700
Data Index: 2711995 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1859. Min Range: -5.1859
Max Act: 4.9984. Min Act: -0.1700
Data Index: 7347468 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1859. Min Range: -5.1859
Max Act: 4.9672. Min Act: -0.1700
Data Index: 5206843 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1859. Min Range: -5.1859
Max Act: 4.9359. Min Act: -0.1700
Data Index: 1219101 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1859. Min Range: -5.1859
Max Act: 4.9672. Min Act: -0.1700
Data Index: 2354078 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1859. Min Range: -5.1859
Max Act: 4.9672. Min Act: -0.1700
Data Index: 5497462 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1859. Min Range: -5.1859
Max Act: 4.9672. Min Act: -0.1700
Data Index: 5152639 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1859. Min Range: -5.1859
Max Act: 4.9047. Min Act: -0.1700
Data Index: 3027330 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1859. Min Range: -5.1859
Max Act: 4.9359. Min Act: -0.1700
Data Index: 5058552 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1859. Min Range: -5.1859
Max Act: 4.9359. Min Act: -0.1700
Data Index: 3034893 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1859. Min Range: -5.1859
Max Act: 4.9047. Min Act: -0.1700
Data Index: 1965669 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19