Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 109 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3341. Min Range: -5.3341
Max Act: 5.3341. Min Act: -0.1700
Data Index: 2425968 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3341. Min Range: -5.3341
Max Act: 5.2091. Min Act: -0.1700
Data Index: 1092151 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3341. Min Range: -5.3341
Max Act: 5.2091. Min Act: -0.1700
Data Index: 6841608 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3341. Min Range: -5.3341
Max Act: 5.1779. Min Act: -0.1700
Data Index: 6571157 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3341. Min Range: -5.3341
Max Act: 5.1154. Min Act: -0.1700
Data Index: 923993 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3341. Min Range: -5.3341
Max Act: 5.0529. Min Act: -0.1700
Data Index: 1923665 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3341. Min Range: -5.3341
Max Act: 5.0529. Min Act: -0.1700
Data Index: 2490285 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3341. Min Range: -5.3341
Max Act: 5.0841. Min Act: -0.1700
Data Index: 7384503 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3341. Min Range: -5.3341
Max Act: 5.0216. Min Act: -0.1700
Data Index: 402126 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3341. Min Range: -5.3341
Max Act: 4.9904. Min Act: -0.1700
Data Index: 2899955 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3341. Min Range: -5.3341
Max Act: 4.9904. Min Act: -0.1700
Data Index: 1299015 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3341. Min Range: -5.3341
Max Act: 4.9591. Min Act: -0.1700
Data Index: 5793431 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3341. Min Range: -5.3341
Max Act: 4.9591. Min Act: -0.1700
Data Index: 4552532 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3341. Min Range: -5.3341
Max Act: 4.9279. Min Act: -0.1700
Data Index: 6834464 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3341. Min Range: -5.3341
Max Act: 4.8966. Min Act: -0.1700
Data Index: 8419222 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3341. Min Range: -5.3341
Max Act: 4.8966. Min Act: -0.1700
Data Index: 5653520 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3341. Min Range: -5.3341
Max Act: 4.8966. Min Act: -0.1700
Data Index: 1408481 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3341. Min Range: -5.3341
Max Act: 4.8966. Min Act: -0.1700
Data Index: 8814104 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3341. Min Range: -5.3341
Max Act: 4.8654. Min Act: -0.1700
Data Index: 4273186 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3341. Min Range: -5.3341
Max Act: 4.8341. Min Act: -0.1700
Data Index: 1962133 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #19