Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1696 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.5372. Min Act: -0.1700
Data Index: 585232 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.3497. Min Act: -0.1700
Data Index: 2607509 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.3497. Min Act: -0.1700
Data Index: 4201673 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.2872. Min Act: -0.1700
Data Index: 1661046 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.2872. Min Act: -0.1700
Data Index: 1661048 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.2559. Min Act: -0.1700
Data Index: 1830937 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.2247. Min Act: -0.1700
Data Index: 7527901 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.1934. Min Act: -0.1700
Data Index: 4738580 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.1934. Min Act: -0.1700
Data Index: 3961070 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.1934. Min Act: -0.1700
Data Index: 413887 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.1622. Min Act: -0.1700
Data Index: 6766096 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.1622. Min Act: -0.1700
Data Index: 4723761 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.1622. Min Act: -0.1700
Data Index: 4195689 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.1309. Min Act: -0.1700
Data Index: 1008012 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.0997. Min Act: -0.1700
Data Index: 6716977 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.1309. Min Act: -0.1700
Data Index: 1910324 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.1309. Min Act: -0.1700
Data Index: 3829519 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.1309. Min Act: -0.1700
Data Index: 5454532 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.0997. Min Act: -0.1700
Data Index: 3131746 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5372. Min Range: -5.5372
Max Act: 5.0997. Min Act: -0.1700
Data Index: 4149319 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19