Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.7320. Min Act: -0.1700
Data Index: 1204138 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.7007. Min Act: -0.1700
Data Index: 3054386 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.5757. Min Act: -0.1700
Data Index: 2237599 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.4507. Min Act: -0.1700
Data Index: 4144756 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.4507. Min Act: -0.1700
Data Index: 5705360 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.3570. Min Act: -0.1700
Data Index: 7139625 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.3570. Min Act: -0.1700
Data Index: 4121070 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.3257. Min Act: -0.1700
Data Index: 4097943 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.2945. Min Act: -0.1700
Data Index: 42264 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.2945. Min Act: -0.1700
Data Index: 7749178 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.2632. Min Act: -0.1700
Data Index: 8296235 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.2007. Min Act: -0.1700
Data Index: 7596687 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.2320. Min Act: -0.1700
Data Index: 3036619 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.1695. Min Act: -0.1700
Data Index: 8735838 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.2007. Min Act: -0.1700
Data Index: 5103497 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.1695. Min Act: -0.1700
Data Index: 5799377 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.1695. Min Act: -0.1700
Data Index: 8763766 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.1070. Min Act: -0.1700
Data Index: 1510690 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.1382. Min Act: -0.1700
Data Index: 5185804 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7320. Min Range: -5.7320
Max Act: 5.1070. Min Act: -0.1700
Data Index: 127702 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19