Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4639 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.6365. Min Act: -0.1700
Data Index: 1273346 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.5427. Min Act: -0.1700
Data Index: 1532750 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.4802. Min Act: -0.1700
Data Index: 2453890 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.4802. Min Act: -0.1700
Data Index: 4086506 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.4490. Min Act: -0.1700
Data Index: 290008 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.3240. Min Act: -0.1700
Data Index: 6885396 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.3240. Min Act: -0.1700
Data Index: 7730981 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.3240. Min Act: -0.1700
Data Index: 7517985 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.2927. Min Act: -0.1700
Data Index: 4536706 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.2615. Min Act: -0.1700
Data Index: 4919935 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.2302. Min Act: -0.1700
Data Index: 3390401 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.2302. Min Act: -0.1700
Data Index: 5979243 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.2302. Min Act: -0.1700
Data Index: 5668313 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.1677. Min Act: -0.1700
Data Index: 3322883 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.1990. Min Act: -0.1700
Data Index: 480803 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.1677. Min Act: -0.1700
Data Index: 31946 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.1365. Min Act: -0.1700
Data Index: 2891992 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.1677. Min Act: -0.1700
Data Index: 2611945 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.1677. Min Act: -0.1700
Data Index: 601969 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6365. Min Range: -6.6365
Max Act: 6.1365. Min Act: -0.1700
Data Index: 2385051 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19