Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1100 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.3721. Min Act: -0.1700
Data Index: 1900165 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.2784. Min Act: -0.1700
Data Index: 7950857 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.3096. Min Act: -0.1700
Data Index: 5516724 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.3096. Min Act: -0.1696
Data Index: 367992 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.3096. Min Act: -0.1700
Data Index: 6769808 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.3096. Min Act: -0.1700
Data Index: 8174542 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.3096. Min Act: -0.1700
Data Index: 187240 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.3096. Min Act: -0.1700
Data Index: 3441438 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.2784. Min Act: -0.1700
Data Index: 8174532 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.2784. Min Act: -0.1694
Data Index: 7369438 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.3096. Min Act: -0.1700
Data Index: 7625869 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.2784. Min Act: -0.1700
Data Index: 7920596 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.2784. Min Act: -0.1700
Data Index: 5903003 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.2159. Min Act: -0.1700
Data Index: 2481531 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.2471. Min Act: -0.1700
Data Index: 841010 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.2471. Min Act: -0.1700
Data Index: 2226539 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.2471. Min Act: -0.1700
Data Index: 5276126 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.2471. Min Act: -0.1700
Data Index: 2624343 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.2784. Min Act: -0.1700
Data Index: 5516714 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3721. Min Range: -4.3721
Max Act: 4.2471. Min Act: -0.1699
Data Index: 402905 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #19