Model: None
Dataset: The Pile
Neuron 420 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.8055. Min Act: -0.1700
Data Index: 3504556 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.8055. Min Act: -0.1700
Data Index: 5342696 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7742. Min Act: -0.1700
Data Index: 8625640 (The Pile)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7742. Min Act: -0.1700
Data Index: 1826894 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7742. Min Act: -0.1700
Data Index: 9570267 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7742. Min Act: -0.1700
Data Index: 5090685 (The Pile)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7742. Min Act: -0.1700
Data Index: 4353540 (The Pile)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7742. Min Act: -0.1700
Data Index: 274236 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7430. Min Act: -0.1700
Data Index: 7906284 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7430. Min Act: -0.1700
Data Index: 8356961 (The Pile)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7430. Min Act: -0.1700
Data Index: 2165373 (The Pile)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7430. Min Act: -0.1700
Data Index: 1418547 (The Pile)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7430. Min Act: -0.1700
Data Index: 5677046 (The Pile)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7430. Min Act: -0.1700
Data Index: 5625088 (The Pile)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7430. Min Act: -0.1700
Data Index: 2975904 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7430. Min Act: -0.1700
Data Index: 5593719 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7430. Min Act: -0.1700
Data Index: 5252210 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7430. Min Act: -0.1700
Data Index: 8716905 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7117. Min Act: -0.1700
Data Index: 4088634 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8055. Min Range: -3.8055
Max Act: 3.7117. Min Act: -0.1700
Data Index: 7842378 (The Pile)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19