Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2815 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.2305. Min Act: -0.1700
Data Index: 7261696 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.1055. Min Act: -0.1700
Data Index: 4029902 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.1055. Min Act: -0.1700
Data Index: 3800495 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.1055. Min Act: -0.1700
Data Index: 4729084 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.1055. Min Act: -0.1700
Data Index: 7468727 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0742. Min Act: -0.1700
Data Index: 3915458 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0430. Min Act: -0.1700
Data Index: 6081875 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0742. Min Act: -0.1700
Data Index: 3550139 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.1055. Min Act: -0.1700
Data Index: 5372361 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0742. Min Act: -0.1700
Data Index: 1813395 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0430. Min Act: -0.1700
Data Index: 7369424 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0430. Min Act: -0.1700
Data Index: 1451950 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0430. Min Act: -0.1700
Data Index: 919743 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0430. Min Act: -0.1700
Data Index: 4401986 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0430. Min Act: -0.1700
Data Index: 2728097 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0742. Min Act: -0.1700
Data Index: 1319834 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0430. Min Act: -0.1700
Data Index: 8108744 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0430. Min Act: -0.1700
Data Index: 4597452 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0117. Min Act: -0.1700
Data Index: 839180 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2305. Min Range: -4.2305
Max Act: 4.0117. Min Act: -0.1700
Data Index: 3867557 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #19