Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2453 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7903. Min Act: -0.1700
Data Index: 6715234 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7590. Min Act: -0.1700
Data Index: 7348414 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7903. Min Act: -0.1700
Data Index: 8337808 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7590. Min Act: -0.1700
Data Index: 1843899 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7278. Min Act: -0.1700
Data Index: 4512959 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.7278. Min Act: -0.1700
Data Index: 4978160 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6340. Min Act: -0.1700
Data Index: 4534942 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6340. Min Act: -0.1700
Data Index: 2854341 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6028. Min Act: -0.1700
Data Index: 6092299 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6028. Min Act: -0.1700
Data Index: 1272916 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.5715. Min Act: -0.1700
Data Index: 7250689 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6028. Min Act: -0.1700
Data Index: 6743825 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.6028. Min Act: -0.1700
Data Index: 6350033 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.5715. Min Act: -0.1700
Data Index: 4082829 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.5715. Min Act: -0.1700
Data Index: 4103116 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.5715. Min Act: -0.1700
Data Index: 3172831 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.5403. Min Act: -0.1700
Data Index: 4755886 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.5715. Min Act: -0.1700
Data Index: 370535 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.5715. Min Act: -0.1700
Data Index: 3203258 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7903. Min Range: -4.7903
Max Act: 4.5715. Min Act: -0.1700
Data Index: 7616891 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19