Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5956 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.7187. Min Act: -0.1700
Data Index: 6030189 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.6250. Min Act: -0.1700
Data Index: 1786217 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.6250. Min Act: -0.1700
Data Index: 2945920 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.5937. Min Act: -0.1700
Data Index: 4791068 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.5937. Min Act: -0.1700
Data Index: 4667171 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.5625. Min Act: -0.1700
Data Index: 1660089 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.5312. Min Act: -0.1700
Data Index: 4931321 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.5312. Min Act: -0.1700
Data Index: 84391 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.5625. Min Act: -0.1700
Data Index: 6929380 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.4687. Min Act: -0.1700
Data Index: 4907592 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.5000. Min Act: -0.1700
Data Index: 3359689 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.5000. Min Act: -0.1700
Data Index: 7177026 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.5000. Min Act: -0.1700
Data Index: 5299352 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.5000. Min Act: -0.1700
Data Index: 3431440 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.5000. Min Act: -0.1700
Data Index: 1581414 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.4687. Min Act: -0.1700
Data Index: 4561115 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.4687. Min Act: -0.1700
Data Index: 1635120 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.4687. Min Act: -0.1700
Data Index: 6365026 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.4687. Min Act: -0.1700
Data Index: 5990435 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7187. Min Range: -5.7187
Max Act: 5.4375. Min Act: -0.1700
Data Index: 1098414 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19