Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3501 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.7999. Min Act: -0.1700
Data Index: 1575447 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.6749. Min Act: -0.1700
Data Index: 4403235 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.6124. Min Act: -0.1700
Data Index: 3879511 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.5499. Min Act: -0.1700
Data Index: 343030 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.5499. Min Act: -0.1700
Data Index: 292589 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.4874. Min Act: -0.1700
Data Index: 8602988 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.3624. Min Act: -0.1700
Data Index: 3297653 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.3624. Min Act: -0.1700
Data Index: 82772 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.2999. Min Act: -0.1700
Data Index: 4399363 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.2999. Min Act: -0.1700
Data Index: 1903186 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.3624. Min Act: -0.1700
Data Index: 8407686 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.2999. Min Act: -0.1700
Data Index: 4712144 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.2374. Min Act: -0.1700
Data Index: 4945441 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.2374. Min Act: -0.1700
Data Index: 6530189 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.1749. Min Act: -0.1700
Data Index: 3674655 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.1749. Min Act: -0.1700
Data Index: 7031872 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.1749. Min Act: -0.1700
Data Index: 6110914 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.1124. Min Act: -0.1700
Data Index: 7145362 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.1124. Min Act: -0.1700
Data Index: 900392 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7999. Min Range: -9.7999
Max Act: 9.1124. Min Act: -0.1700
Data Index: 3181492 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #19