Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2028 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.5861. Min Act: -0.1700
Data Index: 3800221 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.4611. Min Act: -0.1700
Data Index: 3337900 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.3361. Min Act: -0.1700
Data Index: 5472852 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.2736. Min Act: -0.1700
Data Index: 3031292 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.2736. Min Act: -0.1700
Data Index: 3085257 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.2111. Min Act: -0.1700
Data Index: 374021 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.1798. Min Act: -0.1700
Data Index: 5077707 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.1486. Min Act: -0.1700
Data Index: 2031487 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.1173. Min Act: -0.1700
Data Index: 4532038 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.1173. Min Act: -0.1700
Data Index: 1712617 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.0861. Min Act: -0.1700
Data Index: 3765600 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.0548. Min Act: -0.1700
Data Index: 7728830 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.0548. Min Act: -0.1700
Data Index: 5870025 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.0861. Min Act: -0.1700
Data Index: 6511505 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.0236. Min Act: -0.1700
Data Index: 45515 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.0236. Min Act: -0.1700
Data Index: 6147063 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.0236. Min Act: -0.1700
Data Index: 5140710 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5861. Min Range: -5.5861
Max Act: 5.0236. Min Act: -0.1700
Data Index: 117958 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5861. Min Range: -5.5861
Max Act: 4.9923. Min Act: -0.1700
Data Index: 4854510 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5861. Min Range: -5.5861
Max Act: 4.9923. Min Act: -0.1700
Data Index: 7526390 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #19