Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 866 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.5270. Min Act: -0.1700
Data Index: 7657190 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.4020. Min Act: -0.1700
Data Index: 1419977 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.4333. Min Act: -0.1700
Data Index: 4786608 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.4020. Min Act: -0.1700
Data Index: 6726793 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.4333. Min Act: -0.1700
Data Index: 2582934 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.3395. Min Act: -0.1700
Data Index: 7982197 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.3707. Min Act: -0.1700
Data Index: 63517 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.3707. Min Act: -0.1700
Data Index: 5354350 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.3707. Min Act: -0.1700
Data Index: 1858887 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.3395. Min Act: -0.1700
Data Index: 4574945 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.3395. Min Act: -0.1700
Data Index: 3399353 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.3082. Min Act: -0.1700
Data Index: 1020528 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.3082. Min Act: -0.1700
Data Index: 2895812 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.3082. Min Act: -0.1700
Data Index: 2995598 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.2770. Min Act: -0.1700
Data Index: 122304 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.3082. Min Act: -0.1700
Data Index: 3297528 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.2457. Min Act: -0.1700
Data Index: 4481243 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.2457. Min Act: -0.1700
Data Index: 5121766 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.2457. Min Act: -0.1700
Data Index: 1279467 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5270. Min Range: -4.5270
Max Act: 4.3082. Min Act: -0.1700
Data Index: 454573 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19