Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3898 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.6830. Min Act: -0.1700
Data Index: 1244832 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.6361. Min Act: -0.1700
Data Index: 2727698 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.6204. Min Act: -0.1700
Data Index: 7736234 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.6204. Min Act: -0.1700
Data Index: 6632706 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.6517. Min Act: -0.1700
Data Index: 4423167 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.6204. Min Act: -0.1700
Data Index: 8453165 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5891. Min Act: -0.1700
Data Index: 1452607 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5891. Min Act: -0.1700
Data Index: 1246117 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5578. Min Act: -0.1700
Data Index: 4226057 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5735. Min Act: -0.1700
Data Index: 5556497 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5578. Min Act: -0.1700
Data Index: 7497095 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5421. Min Act: -0.1700
Data Index: 4668526 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5421. Min Act: -0.1700
Data Index: 4343773 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5421. Min Act: -0.1700
Data Index: 6842826 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5421. Min Act: -0.1700
Data Index: 5817647 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5265. Min Act: -0.1700
Data Index: 6016871 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5421. Min Act: -0.1700
Data Index: 1117297 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5265. Min Act: -0.1700
Data Index: 4623539 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.5108. Min Act: -0.1700
Data Index: 257713 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6830. Min Range: -3.6830
Max Act: 3.4952. Min Act: -0.1700
Data Index: 1828230 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19