Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2410 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.7744. Min Act: -0.1700
Data Index: 1416606 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.3994. Min Act: -0.1700
Data Index: 2724853 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.3994. Min Act: -0.1700
Data Index: 184923 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.2744. Min Act: -0.1700
Data Index: 6105075 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.3369. Min Act: -0.1700
Data Index: 6803839 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.2119. Min Act: -0.1700
Data Index: 2192292 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.2119. Min Act: -0.1700
Data Index: 408914 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.2119. Min Act: -0.1700
Data Index: 2701308 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.2119. Min Act: -0.1700
Data Index: 4351681 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.2119. Min Act: -0.1700
Data Index: 7852890 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.1494. Min Act: -0.1700
Data Index: 8494896 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.1494. Min Act: -0.1700
Data Index: 1845332 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.1494. Min Act: -0.1700
Data Index: 3101761 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.1494. Min Act: -0.1700
Data Index: 98469 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.1494. Min Act: -0.1700
Data Index: 7767241 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.1494. Min Act: -0.1700
Data Index: 7313528 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.1494. Min Act: -0.1700
Data Index: 3323881 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.0869. Min Act: -0.1700
Data Index: 6233527 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.0244. Min Act: -0.1700
Data Index: 6840139 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7744. Min Range: -9.7744
Max Act: 9.0869. Min Act: -0.1700
Data Index: 1599871 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19