Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 855 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.4869. Min Range: -8.4869
Max Act: 8.4869. Min Act: -0.1700
Data Index: 3244348 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4869. Min Range: -8.4869
Max Act: 8.4244. Min Act: -0.1700
Data Index: 6420937 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4869. Min Range: -8.4869
Max Act: 8.3931. Min Act: -0.1700
Data Index: 2335425 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4869. Min Range: -8.4869
Max Act: 8.3619. Min Act: -0.1700
Data Index: 7955658 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4869. Min Range: -8.4869
Max Act: 8.2681. Min Act: -0.1700
Data Index: 6911257 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4869. Min Range: -8.4869
Max Act: 8.1744. Min Act: -0.1700
Data Index: 2743441 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4869. Min Range: -8.4869
Max Act: 8.0181. Min Act: -0.1700
Data Index: 4709027 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4869. Min Range: -8.4869
Max Act: 8.0181. Min Act: -0.1700
Data Index: 7157565 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4869. Min Range: -8.4869
Max Act: 7.9869. Min Act: -0.1700
Data Index: 7580209 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4869. Min Range: -8.4869
Max Act: 7.9869. Min Act: -0.1700
Data Index: 3564965 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4869. Min Range: -8.4869
Max Act: 7.9556. Min Act: -0.1700
Data Index: 3511665 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4869. Min Range: -8.4869
Max Act: 7.9556. Min Act: -0.1700
Data Index: 3739321 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4869. Min Range: -8.4869
Max Act: 7.9556. Min Act: -0.1700
Data Index: 326720 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4869. Min Range: -8.4869
Max Act: 7.8931. Min Act: -0.1700
Data Index: 2534838 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4869. Min Range: -8.4869
Max Act: 7.8931. Min Act: -0.1700
Data Index: 5396194 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4869. Min Range: -8.4869
Max Act: 7.8619. Min Act: -0.1700
Data Index: 497719 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4869. Min Range: -8.4869
Max Act: 7.8306. Min Act: -0.1700
Data Index: 266836 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4869. Min Range: -8.4869
Max Act: 7.8306. Min Act: -0.1700
Data Index: 2111008 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4869. Min Range: -8.4869
Max Act: 7.8619. Min Act: -0.1700
Data Index: 6626176 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4869. Min Range: -8.4869
Max Act: 7.8619. Min Act: -0.1700
Data Index: 3859235 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19