Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1417 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.7514. Min Act: -0.1700
Data Index: 79437 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.6577. Min Act: -0.1700
Data Index: 7640376 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.6264. Min Act: -0.1700
Data Index: 6548902 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.5639. Min Act: -0.1700
Data Index: 7253142 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.5014. Min Act: -0.1700
Data Index: 6591665 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.4389. Min Act: -0.1700
Data Index: 6343436 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.4077. Min Act: -0.1700
Data Index: 5763027 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.3764. Min Act: -0.1700
Data Index: 4355679 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.3452. Min Act: -0.1700
Data Index: 4069093 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.3139. Min Act: -0.1700
Data Index: 8406586 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.3764. Min Act: -0.1700
Data Index: 662457 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.3139. Min Act: -0.1700
Data Index: 2039897 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.2827. Min Act: -0.1700
Data Index: 6567557 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.2827. Min Act: -0.1700
Data Index: 7017250 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.3139. Min Act: -0.1700
Data Index: 2373328 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.2202. Min Act: -0.1700
Data Index: 4769845 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.2202. Min Act: -0.1700
Data Index: 2093997 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.2514. Min Act: -0.1700
Data Index: 2926995 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.2514. Min Act: -0.1700
Data Index: 6201192 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7514. Min Range: -6.7514
Max Act: 6.2202. Min Act: -0.1700
Data Index: 6309211 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19