Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3687 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.7823. Min Act: -0.1700
Data Index: 6452419 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.5948. Min Act: -0.1700
Data Index: 5751144 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.5635. Min Act: -0.1700
Data Index: 717380 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.5635. Min Act: -0.1700
Data Index: 7447942 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.5323. Min Act: -0.1700
Data Index: 7771432 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.5635. Min Act: -0.1700
Data Index: 1541373 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.5635. Min Act: -0.1700
Data Index: 3158103 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.5635. Min Act: -0.1700
Data Index: 440031 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.5010. Min Act: -0.1700
Data Index: 2359950 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.5010. Min Act: -0.1700
Data Index: 2001290 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.4698. Min Act: -0.1700
Data Index: 5489903 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.4698. Min Act: -0.1700
Data Index: 3765115 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.4385. Min Act: -0.1700
Data Index: 4336580 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.4073. Min Act: -0.1700
Data Index: 209457 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.4385. Min Act: -0.1700
Data Index: 551025 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.4073. Min Act: -0.1700
Data Index: 6452413 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.4073. Min Act: -0.1700
Data Index: 5283555 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.4073. Min Act: -0.1700
Data Index: 4114934 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.3760. Min Act: -0.1700
Data Index: 4501520 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7823. Min Range: -4.7823
Max Act: 4.3760. Min Act: -0.1700
Data Index: 4631229 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19