Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5407 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.4689. Min Act: -0.1700
Data Index: 3320542 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.3439. Min Act: -0.1700
Data Index: 52364 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.2814. Min Act: -0.1700
Data Index: 8439234 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.2501. Min Act: -0.1700
Data Index: 6836612 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.2189. Min Act: -0.1700
Data Index: 3085704 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.1876. Min Act: -0.1700
Data Index: 8660884 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.1876. Min Act: -0.1700
Data Index: 6283562 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.1564. Min Act: -0.1700
Data Index: 158326 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.1564. Min Act: -0.1700
Data Index: 670100 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.0939. Min Act: -0.1700
Data Index: 4086722 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.0939. Min Act: -0.1700
Data Index: 6295772 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.0626. Min Act: -0.1700
Data Index: 1287407 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.0626. Min Act: -0.1700
Data Index: 6875366 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.0314. Min Act: -0.1700
Data Index: 1876003 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.0001. Min Act: -0.1700
Data Index: 6908992 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.0001. Min Act: -0.1700
Data Index: 6110455 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.0001. Min Act: -0.1700
Data Index: 6454468 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4689. Min Range: -6.4689
Max Act: 6.0001. Min Act: -0.1700
Data Index: 1942085 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4689. Min Range: -6.4689
Max Act: 5.9689. Min Act: -0.1700
Data Index: 6666865 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4689. Min Range: -6.4689
Max Act: 5.9689. Min Act: -0.1700
Data Index: 7464870 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19