Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3992 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.9993. Min Act: -0.1700
Data Index: 5431255 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.7181. Min Act: -0.1700
Data Index: 1004435 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.6868. Min Act: -0.1700
Data Index: 3820502 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.5618. Min Act: -0.1700
Data Index: 5916585 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.4993. Min Act: -0.1700
Data Index: 1301295 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.4056. Min Act: -0.1700
Data Index: 7537407 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.4368. Min Act: -0.1700
Data Index: 8798364 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.4368. Min Act: -0.1700
Data Index: 8392466 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.4368. Min Act: -0.1700
Data Index: 3316484 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.3743. Min Act: -0.1700
Data Index: 6143265 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.3431. Min Act: -0.1700
Data Index: 6511604 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.3431. Min Act: -0.1700
Data Index: 1540469 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.3431. Min Act: -0.1700
Data Index: 1858283 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.2806. Min Act: -0.1700
Data Index: 5071503 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.2806. Min Act: -0.1700
Data Index: 6769743 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.2806. Min Act: -0.1700
Data Index: 2444490 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.2806. Min Act: -0.1700
Data Index: 7551509 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.2806. Min Act: -0.1700
Data Index: 4620196 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.2493. Min Act: -0.1700
Data Index: 7816070 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9993. Min Range: -6.9993
Max Act: 6.2181. Min Act: -0.1700
Data Index: 6258348 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19