Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 986 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.4945. Min Act: -0.1700
Data Index: 8187484 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.4945. Min Act: -0.1700
Data Index: 6196329 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.4632. Min Act: -0.1700
Data Index: 4500932 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.4007. Min Act: -0.1700
Data Index: 3698358 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.4007. Min Act: -0.1700
Data Index: 4937606 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3695. Min Act: -0.1700
Data Index: 7494126 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3695. Min Act: -0.1700
Data Index: 3698360 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3695. Min Act: -0.1700
Data Index: 3698356 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3382. Min Act: -0.1700
Data Index: 6970727 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3382. Min Act: -0.1700
Data Index: 2568020 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2757. Min Act: -0.1700
Data Index: 2568021 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3070. Min Act: -0.1700
Data Index: 2241294 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3070. Min Act: -0.1700
Data Index: 6196323 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.3070. Min Act: -0.1700
Data Index: 695332 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2757. Min Act: -0.1700
Data Index: 1023980 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2757. Min Act: -0.1700
Data Index: 635938 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2757. Min Act: -0.1700
Data Index: 2506111 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2757. Min Act: -0.1700
Data Index: 2500033 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2757. Min Act: -0.1700
Data Index: 4864791 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4945. Min Range: -5.4945
Max Act: 5.2445. Min Act: -0.1700
Data Index: 231671 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19