Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3864 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.8574. Min Act: -0.1700
Data Index: 8437379 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.7949. Min Act: -0.1700
Data Index: 5499744 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.7324. Min Act: -0.1700
Data Index: 7180529 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.4512. Min Act: -0.1700
Data Index: 7911432 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.4199. Min Act: -0.1700
Data Index: 4135392 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.4199. Min Act: -0.1700
Data Index: 2935707 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.4199. Min Act: -0.1700
Data Index: 5602806 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.3887. Min Act: -0.1700
Data Index: 2149675 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.3574. Min Act: -0.1700
Data Index: 4939242 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.3262. Min Act: -0.1700
Data Index: 1714431 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.3262. Min Act: -0.1700
Data Index: 6449421 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.3262. Min Act: -0.1700
Data Index: 6601326 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.2949. Min Act: -0.1700
Data Index: 1840538 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.3262. Min Act: -0.1700
Data Index: 2276763 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.2637. Min Act: -0.1700
Data Index: 5058903 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.2637. Min Act: -0.1700
Data Index: 6961409 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.2637. Min Act: -0.1700
Data Index: 6321778 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.2324. Min Act: -0.1700
Data Index: 2805846 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.2324. Min Act: -0.1700
Data Index: 7635769 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8574. Min Range: -7.8574
Max Act: 7.2324. Min Act: -0.1700
Data Index: 3564139 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19