Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 568 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2020. Min Range: -6.2020
Max Act: 6.2020. Min Act: -0.1700
Data Index: 4954093 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2020. Min Range: -6.2020
Max Act: 6.0145. Min Act: -0.1700
Data Index: 2257832 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2020. Min Range: -6.2020
Max Act: 6.0457. Min Act: -0.1699
Data Index: 4303611 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2020. Min Range: -6.2020
Max Act: 6.0145. Min Act: -0.1700
Data Index: 4862163 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.9832. Min Act: -0.1700
Data Index: 4793349 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.9832. Min Act: -0.1700
Data Index: 5344730 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.9520. Min Act: -0.1700
Data Index: 6754034 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.9207. Min Act: -0.1700
Data Index: 2394986 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.9207. Min Act: -0.1700
Data Index: 110687 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.9207. Min Act: -0.1700
Data Index: 5467993 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.8582. Min Act: -0.1700
Data Index: 3776579 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.8895. Min Act: -0.1700
Data Index: 6829213 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.8895. Min Act: -0.1700
Data Index: 6143023 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.8895. Min Act: -0.1700
Data Index: 6042277 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.8582. Min Act: -0.1700
Data Index: 6607225 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.8582. Min Act: -0.1700
Data Index: 8352666 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.8582. Min Act: -0.1700
Data Index: 4033318 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.8270. Min Act: -0.1700
Data Index: 2768262 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.8270. Min Act: -0.1700
Data Index: 8738445 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2020. Min Range: -6.2020
Max Act: 5.8270. Min Act: -0.1700
Data Index: 3432167 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #19