Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 273 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.5437. Min Act: -0.1700
Data Index: 5448889 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.5124. Min Act: -0.1700
Data Index: 610087 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.4499. Min Act: -0.1700
Data Index: 4353371 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.4187. Min Act: -0.1700
Data Index: 8513853 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.4499. Min Act: -0.1700
Data Index: 5054362 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.4499. Min Act: -0.1700
Data Index: 3472568 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.3562. Min Act: -0.1700
Data Index: 5380924 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.3874. Min Act: -0.1700
Data Index: 1149629 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.3874. Min Act: -0.1700
Data Index: 7879766 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.3562. Min Act: -0.1700
Data Index: 5058511 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.3562. Min Act: -0.1700
Data Index: 4899038 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.3562. Min Act: -0.1700
Data Index: 5790653 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.3249. Min Act: -0.1700
Data Index: 6214167 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.2936. Min Act: -0.1700
Data Index: 4880002 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.2936. Min Act: -0.1700
Data Index: 2418473 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.2936. Min Act: -0.1700
Data Index: 7221376 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.2311. Min Act: -0.1700
Data Index: 3696056 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.2936. Min Act: -0.1700
Data Index: 7624425 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.2936. Min Act: -0.1700
Data Index: 290887 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5437. Min Range: -4.5437
Max Act: 4.2311. Min Act: -0.1700
Data Index: 485435 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19