Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 991 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0792. Min Range: -4.0792
Max Act: 4.0792. Min Act: -0.1700
Data Index: 7842273 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.9854. Min Act: -0.1700
Data Index: 5732035 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.9541. Min Act: -0.1700
Data Index: 2591084 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.9229. Min Act: -0.1700
Data Index: 5732034 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.8916. Min Act: -0.1700
Data Index: 997046 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.7665. Min Act: -0.1700
Data Index: 6394131 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.7978. Min Act: -0.1700
Data Index: 6013284 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.7352. Min Act: -0.1700
Data Index: 6214512 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.7352. Min Act: -0.1700
Data Index: 6518025 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.7196. Min Act: -0.1700
Data Index: 4148076 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.7352. Min Act: -0.1700
Data Index: 2214331 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.7352. Min Act: -0.1700
Data Index: 181897 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.7352. Min Act: -0.1700
Data Index: 3181970 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.7039. Min Act: -0.1700
Data Index: 4193129 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.7039. Min Act: -0.1700
Data Index: 3607182 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.6727. Min Act: -0.1700
Data Index: 998690 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.6883. Min Act: -0.1700
Data Index: 3415356 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.6570. Min Act: -0.1700
Data Index: 470686 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.6883. Min Act: -0.1700
Data Index: 7894870 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0792. Min Range: -4.0792
Max Act: 3.7039. Min Act: -0.1700
Data Index: 3894129 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19