Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3271 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3443. Min Range: -4.3443
Max Act: 4.3443. Min Act: -0.1700
Data Index: 3453235 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3443. Min Range: -4.3443
Max Act: 4.3130. Min Act: -0.1700
Data Index: 8495306 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3443. Min Range: -4.3443
Max Act: 4.1255. Min Act: -0.1700
Data Index: 5088769 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3443. Min Range: -4.3443
Max Act: 4.0942. Min Act: -0.1700
Data Index: 1649884 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3443. Min Range: -4.3443
Max Act: 4.0942. Min Act: -0.1700
Data Index: 128547 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3443. Min Range: -4.3443
Max Act: 4.0317. Min Act: -0.1700
Data Index: 7235531 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.9379. Min Act: -0.1700
Data Index: 5087773 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.9692. Min Act: -0.1700
Data Index: 5473177 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.9379. Min Act: -0.1700
Data Index: 7383008 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.9379. Min Act: -0.1700
Data Index: 5979144 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.8754. Min Act: -0.1700
Data Index: 4334724 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.8441. Min Act: -0.1700
Data Index: 2072384 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.8128. Min Act: -0.1700
Data Index: 2607665 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.8441. Min Act: -0.1700
Data Index: 1727462 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.8128. Min Act: -0.1700
Data Index: 4893147 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.8128. Min Act: -0.1700
Data Index: 1765979 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.8128. Min Act: -0.1700
Data Index: 3095854 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.7816. Min Act: -0.1700
Data Index: 7482717 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.7190. Min Act: -0.1700
Data Index: 6517024 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3443. Min Range: -4.3443
Max Act: 3.7503. Min Act: -0.1700
Data Index: 6711002 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19