Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1507 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.1008. Min Act: -0.1700
Data Index: 4784631 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.1008. Min Act: -0.1700
Data Index: 1346517 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.1634. Min Act: -0.1700
Data Index: 937531 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0696. Min Act: -0.1700
Data Index: 3829996 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.1008. Min Act: -0.1700
Data Index: 8690143 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0696. Min Act: -0.1700
Data Index: 1072514 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0696. Min Act: -0.1700
Data Index: 1702708 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0383. Min Act: -0.1700
Data Index: 937534 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0696. Min Act: -0.1700
Data Index: 6560505 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0383. Min Act: -0.1700
Data Index: 7671009 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0696. Min Act: -0.1700
Data Index: 2504525 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0383. Min Act: -0.1700
Data Index: 368440 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0696. Min Act: -0.1700
Data Index: 4660335 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0383. Min Act: -0.1700
Data Index: 647169 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1634. Min Range: -4.1634
Max Act: 3.9445. Min Act: -0.1700
Data Index: 4339418 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0383. Min Act: -0.1700
Data Index: 4179550 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0383. Min Act: -0.1700
Data Index: 6693943 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1634. Min Range: -4.1634
Max Act: 4.0383. Min Act: -0.1700
Data Index: 1316572 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1634. Min Range: -4.1634
Max Act: 3.9758. Min Act: -0.1700
Data Index: 1072515 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1634. Min Range: -4.1634
Max Act: 3.9758. Min Act: -0.1700
Data Index: 1504405 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19