Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 786 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.8424. Min Act: -0.1700
Data Index: 4657998 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.7955. Min Act: -0.1700
Data Index: 6727745 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.7643. Min Act: -0.1700
Data Index: 2259439 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.7486. Min Act: -0.1700
Data Index: 4814232 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.7017. Min Act: -0.1700
Data Index: 723045 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.5922. Min Act: -0.1700
Data Index: 2624773 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.6078. Min Act: -0.1700
Data Index: 7505014 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.5765. Min Act: -0.1700
Data Index: 4522468 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.5609. Min Act: -0.1700
Data Index: 3513792 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.5295. Min Act: -0.1700
Data Index: 4468913 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.5452. Min Act: -0.1700
Data Index: 3089927 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.4826. Min Act: -0.1700
Data Index: 1001146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.4356. Min Act: -0.1700
Data Index: 5688290 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.4356. Min Act: -0.1700
Data Index: 778623 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.4982. Min Act: -0.1700
Data Index: 47184 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.4512. Min Act: -0.1700
Data Index: 1311649 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.4512. Min Act: -0.1700
Data Index: 3484522 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.4512. Min Act: -0.1700
Data Index: 3123675 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.4356. Min Act: -0.1700
Data Index: 6769312 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8424. Min Range: -3.8424
Max Act: 3.4512. Min Act: -0.1700
Data Index: 5299161 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19