Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 589 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.5282. Min Act: -0.1700
Data Index: 6227771 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.4969. Min Act: -0.1700
Data Index: 8625869 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.2157. Min Act: -0.1700
Data Index: 6483994 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.2157. Min Act: -0.1700
Data Index: 6503389 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.1844. Min Act: -0.1700
Data Index: 4839243 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.1844. Min Act: -0.1700
Data Index: 6629009 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.1532. Min Act: -0.1700
Data Index: 6259124 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.1532. Min Act: -0.1700
Data Index: 377038 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.1219. Min Act: -0.1700
Data Index: 5914652 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.1844. Min Act: -0.1700
Data Index: 960745 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.0907. Min Act: -0.1700
Data Index: 2980099 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.0907. Min Act: -0.1700
Data Index: 2921798 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.0907. Min Act: -0.1700
Data Index: 5557274 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.0594. Min Act: -0.1700
Data Index: 7731892 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.0907. Min Act: -0.1700
Data Index: 5453126 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.0594. Min Act: -0.1700
Data Index: 2011365 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.0907. Min Act: -0.1700
Data Index: 5551150 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.0594. Min Act: -0.1700
Data Index: 6256214 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5282. Min Range: -5.5282
Max Act: 5.0282. Min Act: -0.1700
Data Index: 8282896 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5282. Min Range: -5.5282
Max Act: 4.9969. Min Act: -0.1700
Data Index: 5170974 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19