Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1573 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.3393. Min Act: -0.1700
Data Index: 4937981 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.3081. Min Act: -0.1700
Data Index: 535928 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.2456. Min Act: -0.1700
Data Index: 3734711 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.2143. Min Act: -0.1700
Data Index: 2987171 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.2143. Min Act: -0.1700
Data Index: 4698104 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.1831. Min Act: -0.1700
Data Index: 8474991 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.1518. Min Act: -0.1700
Data Index: 407332 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.1831. Min Act: -0.1700
Data Index: 8451183 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.1831. Min Act: -0.1700
Data Index: 6118072 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.1518. Min Act: -0.1700
Data Index: 7680584 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.1518. Min Act: -0.1700
Data Index: 2279519 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.1518. Min Act: -0.1700
Data Index: 2609275 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.1206. Min Act: -0.1700
Data Index: 2076846 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.0893. Min Act: -0.1700
Data Index: 161634 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.0893. Min Act: -0.1700
Data Index: 2820924 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.0581. Min Act: -0.1700
Data Index: 6456256 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.0893. Min Act: -0.1700
Data Index: 8642478 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.0581. Min Act: -0.1700
Data Index: 8278487 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.0581. Min Act: -0.1700
Data Index: 4669392 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3393. Min Range: -5.3393
Max Act: 5.0893. Min Act: -0.1700
Data Index: 4862216 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19