Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5091 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.9371. Min Act: -0.1700
Data Index: 4149346 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.4996. Min Act: -0.1700
Data Index: 4292898 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.2496. Min Act: -0.1700
Data Index: 6247591 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.2496. Min Act: -0.1700
Data Index: 1720838 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.1871. Min Act: -0.1700
Data Index: 1772577 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.1871. Min Act: -0.1700
Data Index: 2827184 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.1871. Min Act: -0.1700
Data Index: 855154 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.1871. Min Act: -0.1700
Data Index: 8821373 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.1246. Min Act: -0.1700
Data Index: 6662594 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.1246. Min Act: -0.1700
Data Index: 5090181 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.1246. Min Act: -0.1700
Data Index: 6331671 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.0621. Min Act: -0.1700
Data Index: 2559107 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.1246. Min Act: -0.1700
Data Index: 379169 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9371. Min Range: -9.9371
Max Act: 9.0621. Min Act: -0.1700
Data Index: 2280191 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9371. Min Range: -9.9371
Max Act: 8.9996. Min Act: -0.1700
Data Index: 5309108 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9371. Min Range: -9.9371
Max Act: 8.9996. Min Act: -0.1700
Data Index: 7799286 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9371. Min Range: -9.9371
Max Act: 8.9996. Min Act: -0.1700
Data Index: 248623 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9371. Min Range: -9.9371
Max Act: 8.9996. Min Act: -0.1700
Data Index: 5739265 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9371. Min Range: -9.9371
Max Act: 8.9371. Min Act: -0.1700
Data Index: 7665216 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9371. Min Range: -9.9371
Max Act: 8.9996. Min Act: -0.1700
Data Index: 5592740 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #19