Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2286 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2514. Min Range: -5.2514
Max Act: 5.2514. Min Act: -0.1700
Data Index: 1004530 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2514. Min Range: -5.2514
Max Act: 5.1264. Min Act: -0.1700
Data Index: 519074 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2514. Min Range: -5.2514
Max Act: 5.0952. Min Act: -0.1700
Data Index: 8320795 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2514. Min Range: -5.2514
Max Act: 5.0952. Min Act: -0.1700
Data Index: 8538825 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.9702. Min Act: -0.1700
Data Index: 5741980 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.9702. Min Act: -0.1700
Data Index: 69733 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.9389. Min Act: -0.1700
Data Index: 4713636 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.9702. Min Act: -0.1700
Data Index: 1695587 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.9077. Min Act: -0.1700
Data Index: 3823725 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.9077. Min Act: -0.1700
Data Index: 1854351 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.8764. Min Act: -0.1700
Data Index: 752578 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.8764. Min Act: -0.1700
Data Index: 130239 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.8452. Min Act: -0.1700
Data Index: 2813890 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.8139. Min Act: -0.1700
Data Index: 5563664 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.8139. Min Act: -0.1700
Data Index: 2148314 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.8139. Min Act: -0.1700
Data Index: 3823726 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.8139. Min Act: -0.1700
Data Index: 7296909 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.7202. Min Act: -0.1700
Data Index: 332270 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.7514. Min Act: -0.1700
Data Index: 1472093 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2514. Min Range: -5.2514
Max Act: 4.7514. Min Act: -0.1700
Data Index: 8819787 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #19