Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1916 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.3454. Min Act: -0.1700
Data Index: 8389186 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.3454. Min Act: -0.1700
Data Index: 3633083 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.3454. Min Act: -0.1700
Data Index: 7527899 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.3142. Min Act: -0.1700
Data Index: 7877044 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.2517. Min Act: -0.1700
Data Index: 5135632 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.1892. Min Act: -0.1700
Data Index: 3664872 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.1579. Min Act: -0.1700
Data Index: 2943660 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.1267. Min Act: -0.1700
Data Index: 590477 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0954. Min Act: -0.1700
Data Index: 4180611 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.1267. Min Act: -0.1700
Data Index: 944286 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.1267. Min Act: -0.1700
Data Index: 3240551 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0642. Min Act: -0.1700
Data Index: 7605151 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0642. Min Act: -0.1700
Data Index: 4326430 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0642. Min Act: -0.1700
Data Index: 8693031 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0016. Min Act: -0.1700
Data Index: 8027552 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0016. Min Act: -0.1700
Data Index: 5205070 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0329. Min Act: -0.1700
Data Index: 7271799 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0016. Min Act: -0.1700
Data Index: 4843921 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0016. Min Act: -0.1700
Data Index: 5075082 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3454. Min Range: -4.3454
Max Act: 4.0329. Min Act: -0.1700
Data Index: 2143156 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19