Model: None
Dataset: The Pile
Neuron 3278 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.6803. Min Act: -0.1700
Data Index: 7087223 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.6646. Min Act: -0.1700
Data Index: 76025 (The Pile)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.6490. Min Act: -0.1700
Data Index: 8800180 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.6333. Min Act: -0.1700
Data Index: 4677642 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.6177. Min Act: -0.1700
Data Index: 9117975 (The Pile)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5864. Min Act: -0.1700
Data Index: 7442216 (The Pile)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5864. Min Act: -0.1700
Data Index: 95875 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5707. Min Act: -0.1700
Data Index: 6311491 (The Pile)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5551. Min Act: -0.1700
Data Index: 2516858 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5551. Min Act: -0.1700
Data Index: 4906623 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5394. Min Act: -0.1700
Data Index: 1133114 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5394. Min Act: -0.1700
Data Index: 2497277 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5394. Min Act: -0.1700
Data Index: 173816 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5394. Min Act: -0.1700
Data Index: 10569189 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5394. Min Act: -0.1700
Data Index: 4314704 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5394. Min Act: -0.1700
Data Index: 5322271 (The Pile)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5394. Min Act: -0.1700
Data Index: 5127998 (The Pile)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5394. Min Act: -0.1700
Data Index: 10317418 (The Pile)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5394. Min Act: -0.1700
Data Index: 1586905 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6803. Min Range: -3.6803
Max Act: 3.5237. Min Act: -0.1700
Data Index: 9571453 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19