Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2735 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5558. Min Range: -9.5558
Max Act: 9.5558. Min Act: -0.1700
Data Index: 8372386 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5558. Min Range: -9.5558
Max Act: 9.4308. Min Act: -0.1700
Data Index: 8296702 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5558. Min Range: -9.5558
Max Act: 9.3683. Min Act: -0.1700
Data Index: 5323951 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5558. Min Range: -9.5558
Max Act: 9.1808. Min Act: -0.1700
Data Index: 5586059 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5558. Min Range: -9.5558
Max Act: 9.1808. Min Act: -0.1700
Data Index: 8163402 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5558. Min Range: -9.5558
Max Act: 9.1808. Min Act: -0.1700
Data Index: 7711791 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5558. Min Range: -9.5558
Max Act: 9.1183. Min Act: -0.1700
Data Index: 8270033 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5558. Min Range: -9.5558
Max Act: 9.1183. Min Act: -0.1700
Data Index: 5637453 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5558. Min Range: -9.5558
Max Act: 9.1183. Min Act: -0.1700
Data Index: 1229988 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5558. Min Range: -9.5558
Max Act: 9.0558. Min Act: -0.1700
Data Index: 3385518 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5558. Min Range: -9.5558
Max Act: 9.0558. Min Act: -0.1700
Data Index: 829195 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5558. Min Range: -9.5558
Max Act: 8.9933. Min Act: -0.1700
Data Index: 7113829 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5558. Min Range: -9.5558
Max Act: 8.9933. Min Act: -0.1700
Data Index: 564688 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5558. Min Range: -9.5558
Max Act: 8.9933. Min Act: -0.1700
Data Index: 8511343 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5558. Min Range: -9.5558
Max Act: 8.9933. Min Act: -0.1700
Data Index: 6532307 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5558. Min Range: -9.5558
Max Act: 8.9933. Min Act: -0.1700
Data Index: 8127417 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5558. Min Range: -9.5558
Max Act: 8.9308. Min Act: -0.1700
Data Index: 8326304 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5558. Min Range: -9.5558
Max Act: 8.9308. Min Act: -0.1700
Data Index: 6914409 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5558. Min Range: -9.5558
Max Act: 8.8683. Min Act: -0.1700
Data Index: 6031251 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5558. Min Range: -9.5558
Max Act: 8.9308. Min Act: -0.1700
Data Index: 2979079 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19