Model: None
Dataset: The Pile
Neuron 3520 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.6175. Min Act: -0.1700
Data Index: 3231134 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.6175. Min Act: -0.1700
Data Index: 6004298 (The Pile)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.6175. Min Act: -0.1700
Data Index: 4085521 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.5549. Min Act: -0.1700
Data Index: 1861351 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.5392. Min Act: -0.1700
Data Index: 6038798 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.5392. Min Act: -0.1700
Data Index: 4226307 (The Pile)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.5236. Min Act: -0.1700
Data Index: 3014949 (The Pile)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.5079. Min Act: -0.1700
Data Index: 3656308 (The Pile)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.5079. Min Act: -0.1700
Data Index: 3531940 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.5079. Min Act: -0.1700
Data Index: 39616 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.4922. Min Act: -0.1700
Data Index: 1867370 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.4922. Min Act: -0.1700
Data Index: 4508261 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.4922. Min Act: -0.1700
Data Index: 1945637 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.4922. Min Act: -0.1700
Data Index: 3992776 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.4922. Min Act: -0.1700
Data Index: 10656987 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.4922. Min Act: -0.1700
Data Index: 6455263 (The Pile)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.4922. Min Act: -0.1700
Data Index: 5065331 (The Pile)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.4766. Min Act: -0.1700
Data Index: 1005839 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.4766. Min Act: -0.1700
Data Index: 5517693 (The Pile)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6175. Min Range: -3.6175
Max Act: 3.4766. Min Act: -0.1700
Data Index: 3201373 (The Pile)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19