Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1949 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.3509. Min Act: -0.1700
Data Index: 6830657 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.3345. Min Act: -0.1700
Data Index: 4586788 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.2522. Min Act: -0.1700
Data Index: 1476721 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.2357. Min Act: -0.1700
Data Index: 4364652 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.1693. Min Act: -0.1700
Data Index: 8128539 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.1860. Min Act: -0.1700
Data Index: 8575178 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.1527. Min Act: -0.1700
Data Index: 5917558 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.1360. Min Act: -0.1700
Data Index: 7885195 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.0690. Min Act: -0.1700
Data Index: 2630146 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.0690. Min Act: -0.1700
Data Index: 5895168 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.0690. Min Act: -0.1700
Data Index: 4180574 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.0522. Min Act: -0.1700
Data Index: 1241641 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.0522. Min Act: -0.1700
Data Index: 4192389 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.0522. Min Act: -0.1700
Data Index: 2504617 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.0354. Min Act: -0.1700
Data Index: 5353047 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.0354. Min Act: -0.1700
Data Index: 148995 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.0354. Min Act: -0.1700
Data Index: 4399199 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.0354. Min Act: -0.1700
Data Index: 3056852 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.0186. Min Act: -0.1700
Data Index: 5423517 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3509. Min Range: -2.3509
Max Act: 2.0186. Min Act: -0.1700
Data Index: 5772232 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #19