Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4049 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.6600. Min Range: -7.6600
Max Act: 7.6600. Min Act: -0.1700
Data Index: 8227951 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6600. Min Range: -7.6600
Max Act: 7.1600. Min Act: -0.1700
Data Index: 5142289 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6600. Min Range: -7.6600
Max Act: 7.1600. Min Act: -0.1700
Data Index: 6871027 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6600. Min Range: -7.6600
Max Act: 7.0975. Min Act: -0.1700
Data Index: 4829490 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6600. Min Range: -7.6600
Max Act: 7.0975. Min Act: -0.1700
Data Index: 3096734 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6600. Min Range: -7.6600
Max Act: 7.0662. Min Act: -0.1700
Data Index: 2810661 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.9725. Min Act: -0.1700
Data Index: 1165559 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.9412. Min Act: -0.1700
Data Index: 6883761 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.9100. Min Act: -0.1700
Data Index: 4490263 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.8787. Min Act: -0.1700
Data Index: 1145157 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.9100. Min Act: -0.1700
Data Index: 901791 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.8787. Min Act: -0.1700
Data Index: 5892474 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.8475. Min Act: -0.1700
Data Index: 3952533 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.8475. Min Act: -0.1700
Data Index: 7541209 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.8475. Min Act: -0.1700
Data Index: 8026857 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.8162. Min Act: -0.1700
Data Index: 4627407 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.8162. Min Act: -0.1700
Data Index: 8410479 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.7850. Min Act: -0.1700
Data Index: 7167449 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.7850. Min Act: -0.1700
Data Index: 914625 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6600. Min Range: -7.6600
Max Act: 6.7850. Min Act: -0.1700
Data Index: 3158324 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19