Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 73 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2428. Min Range: -3.2428
Max Act: 3.2428. Min Act: -0.1700
Data Index: 4241680 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2428. Min Range: -3.2428
Max Act: 3.0539. Min Act: -0.1700
Data Index: 2267071 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2428. Min Range: -3.2428
Max Act: 3.0697. Min Act: -0.1700
Data Index: 522516 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2428. Min Range: -3.2428
Max Act: 3.0697. Min Act: -0.1700
Data Index: 4557999 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2428. Min Range: -3.2428
Max Act: 3.0381. Min Act: -0.1700
Data Index: 6366891 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2428. Min Range: -3.2428
Max Act: 3.0381. Min Act: -0.1700
Data Index: 5367529 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2428. Min Range: -3.2428
Max Act: 3.0223. Min Act: -0.1700
Data Index: 8305135 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2428. Min Range: -3.2428
Max Act: 3.0223. Min Act: -0.1700
Data Index: 2865283 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2428. Min Range: -3.2428
Max Act: 3.0223. Min Act: -0.1700
Data Index: 4240224 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2428. Min Range: -3.2428
Max Act: 3.0065. Min Act: -0.1700
Data Index: 1769306 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2428. Min Range: -3.2428
Max Act: 3.0065. Min Act: -0.1700
Data Index: 2643610 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2428. Min Range: -3.2428
Max Act: 3.0065. Min Act: -0.1700
Data Index: 4584211 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2428. Min Range: -3.2428
Max Act: 2.9907. Min Act: -0.1700
Data Index: 3052522 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2428. Min Range: -3.2428
Max Act: 2.9907. Min Act: -0.1700
Data Index: 5753832 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2428. Min Range: -3.2428
Max Act: 2.9749. Min Act: -0.1700
Data Index: 1978612 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2428. Min Range: -3.2428
Max Act: 2.9749. Min Act: -0.1700
Data Index: 1291803 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2428. Min Range: -3.2428
Max Act: 2.9907. Min Act: -0.1700
Data Index: 717011 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2428. Min Range: -3.2428
Max Act: 2.9749. Min Act: -0.1700
Data Index: 6317820 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2428. Min Range: -3.2428
Max Act: 2.9749. Min Act: -0.1700
Data Index: 6735520 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2428. Min Range: -3.2428
Max Act: 2.9432. Min Act: -0.1700
Data Index: 5673733 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19