Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3106 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1141. Min Range: -9.1141
Max Act: 9.1141. Min Act: -0.1700
Data Index: 4126753 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1141. Min Range: -9.1141
Max Act: 9.1141. Min Act: -0.1700
Data Index: 7881749 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1141. Min Range: -9.1141
Max Act: 9.0516. Min Act: -0.1700
Data Index: 1923608 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1141. Min Range: -9.1141
Max Act: 9.0516. Min Act: -0.1700
Data Index: 2279095 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.9266. Min Act: -0.1700
Data Index: 1378687 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.9266. Min Act: -0.1700
Data Index: 183308 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.9266. Min Act: -0.1700
Data Index: 3292777 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.8641. Min Act: -0.1700
Data Index: 5444719 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.8641. Min Act: -0.1700
Data Index: 1463651 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.8016. Min Act: -0.1700
Data Index: 3905291 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.8016. Min Act: -0.1700
Data Index: 7560092 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.8016. Min Act: -0.1700
Data Index: 2129295 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.7391. Min Act: -0.1700
Data Index: 8651543 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.7391. Min Act: -0.1700
Data Index: 7524928 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.6766. Min Act: -0.1700
Data Index: 3775324 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.7391. Min Act: -0.1700
Data Index: 4865659 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.7391. Min Act: -0.1700
Data Index: 7156315 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.7391. Min Act: -0.1700
Data Index: 2720964 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.7391. Min Act: -0.1700
Data Index: 4560049 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1141. Min Range: -9.1141
Max Act: 8.6766. Min Act: -0.1700
Data Index: 2469094 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19