Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2095 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.5158. Min Act: -0.1700
Data Index: 4621608 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.5470. Min Act: -0.1700
Data Index: 7734768 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.4533. Min Act: -0.1700
Data Index: 321029 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.3595. Min Act: -0.1700
Data Index: 1042321 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.3283. Min Act: -0.1700
Data Index: 7380575 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.2970. Min Act: -0.1700
Data Index: 6449316 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.2658. Min Act: -0.1700
Data Index: 4190655 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.1720. Min Act: -0.1700
Data Index: 6981784 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.2345. Min Act: -0.1700
Data Index: 2383720 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.1720. Min Act: -0.1700
Data Index: 7097344 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.1408. Min Act: -0.1700
Data Index: 4546336 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.1720. Min Act: -0.1700
Data Index: 7275528 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.1408. Min Act: -0.1700
Data Index: 6536344 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.1408. Min Act: -0.1700
Data Index: 5292892 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.0783. Min Act: -0.1700
Data Index: 5634791 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.0783. Min Act: -0.1700
Data Index: 8828960 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.1095. Min Act: -0.1700
Data Index: 7871977 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.0783. Min Act: -0.1700
Data Index: 1873870 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.0158. Min Act: -0.1700
Data Index: 7230262 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5470. Min Range: -5.5470
Max Act: 5.0470. Min Act: -0.1700
Data Index: 5905776 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19