Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 416 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.8414. Min Act: -0.1700
Data Index: 1749629 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.5289. Min Act: -0.1700
Data Index: 5644940 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.5289. Min Act: -0.1700
Data Index: 3687682 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.4977. Min Act: -0.1700
Data Index: 7416385 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.5289. Min Act: -0.1700
Data Index: 1761077 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.4977. Min Act: -0.1700
Data Index: 6937718 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.5289. Min Act: -0.1700
Data Index: 4854200 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.4977. Min Act: -0.1700
Data Index: 1602920 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.4977. Min Act: -0.1700
Data Index: 4937234 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.4664. Min Act: -0.1700
Data Index: 801581 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.4352. Min Act: -0.1700
Data Index: 3240382 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.4039. Min Act: -0.1700
Data Index: 5636530 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.4039. Min Act: -0.1700
Data Index: 1085828 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.4039. Min Act: -0.1700
Data Index: 5107662 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.3726. Min Act: -0.1700
Data Index: 5136610 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.3726. Min Act: -0.1700
Data Index: 6470784 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.3726. Min Act: -0.1700
Data Index: 3515324 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.3726. Min Act: -0.1700
Data Index: 297727 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.3414. Min Act: -0.1700
Data Index: 2409955 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8414. Min Range: -4.8414
Max Act: 4.3101. Min Act: -0.1700
Data Index: 4459505 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19