Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2002 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0624. Min Range: -3.0624
Max Act: 3.0624. Min Act: -0.1700
Data Index: 4822044 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.9518. Min Act: -0.1700
Data Index: 682547 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.9360. Min Act: -0.1700
Data Index: 924926 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8885. Min Act: -0.1700
Data Index: 7703316 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.9043. Min Act: -0.1700
Data Index: 6010457 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8885. Min Act: -0.1700
Data Index: 2571508 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.9043. Min Act: -0.1700
Data Index: 1208942 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8726. Min Act: -0.1700
Data Index: 3648936 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8885. Min Act: -0.1700
Data Index: 4951296 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8726. Min Act: -0.1700
Data Index: 4967741 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8567. Min Act: -0.1700
Data Index: 506938 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8408. Min Act: -0.1700
Data Index: 4057006 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8249. Min Act: -0.1700
Data Index: 362261 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8090. Min Act: -0.1700
Data Index: 3135353 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8408. Min Act: -0.1700
Data Index: 3970161 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8567. Min Act: -0.1700
Data Index: 6475160 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.7931. Min Act: -0.1700
Data Index: 2755425 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8090. Min Act: -0.1700
Data Index: 2440579 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8249. Min Act: -0.1700
Data Index: 5648441 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0624. Min Range: -3.0624
Max Act: 2.8249. Min Act: -0.1700
Data Index: 1329599 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19