Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1794 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1554. Min Range: -4.1554
Max Act: 4.1554. Min Act: -0.1700
Data Index: 6772296 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1554. Min Range: -4.1554
Max Act: 4.0304. Min Act: -0.1700
Data Index: 6397326 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.9678. Min Act: -0.1700
Data Index: 8614654 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.9053. Min Act: -0.1700
Data Index: 6772303 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.9053. Min Act: -0.1700
Data Index: 5137128 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.9053. Min Act: -0.1700
Data Index: 3566649 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.9053. Min Act: -0.1700
Data Index: 8645862 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.9053. Min Act: -0.1700
Data Index: 6069640 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.8584. Min Act: -0.1700
Data Index: 8266824 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.8740. Min Act: -0.1700
Data Index: 8121719 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.8428. Min Act: -0.1700
Data Index: 6772298 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.8428. Min Act: -0.1700
Data Index: 8266827 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.8428. Min Act: -0.1700
Data Index: 5646865 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.8271. Min Act: -0.1700
Data Index: 2134571 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.8115. Min Act: -0.1700
Data Index: 6397335 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.8115. Min Act: -0.1700
Data Index: 1128394 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.8428. Min Act: -0.1700
Data Index: 4321052 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.7959. Min Act: -0.1700
Data Index: 2134557 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.8115. Min Act: -0.1700
Data Index: 252320 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1554. Min Range: -4.1554
Max Act: 3.8115. Min Act: -0.1700
Data Index: 8266800 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19