Model: None
Dataset: The Pile
Neuron 293 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.7086. Min Act: -0.1700
Data Index: 3899276 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.6773. Min Act: -0.1700
Data Index: 2228279 (The Pile)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.6460. Min Act: -0.1700
Data Index: 4851123 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.6460. Min Act: -0.1700
Data Index: 6605845 (The Pile)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.6147. Min Act: -0.1700
Data Index: 334308 (The Pile)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5991. Min Act: -0.1700
Data Index: 6587300 (The Pile)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5991. Min Act: -0.1700
Data Index: 583776 (The Pile)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5991. Min Act: -0.1700
Data Index: 3295121 (The Pile)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5991. Min Act: -0.1700
Data Index: 8542905 (The Pile)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5991. Min Act: -0.1700
Data Index: 8742563 (The Pile)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5991. Min Act: -0.1700
Data Index: 4066233 (The Pile)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5834. Min Act: -0.1700
Data Index: 1722178 (The Pile)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5834. Min Act: -0.1700
Data Index: 187784 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5834. Min Act: -0.1700
Data Index: 4985155 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5677. Min Act: -0.1700
Data Index: 9497530 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5677. Min Act: -0.1700
Data Index: 144744 (The Pile)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5834. Min Act: -0.1700
Data Index: 3920089 (The Pile)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5677. Min Act: -0.1700
Data Index: 1146227 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5677. Min Act: -0.1700
Data Index: 2342625 (The Pile)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7086. Min Range: -3.7086
Max Act: 3.5521. Min Act: -0.1700
Data Index: 8147978 (The Pile)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19