Model: None
Dataset: The Pile
Neuron 441 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.7021. Min Act: -0.1700
Data Index: 7086459 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.4833. Min Act: -0.1700
Data Index: 4682476 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.3896. Min Act: -0.1700
Data Index: 10110654 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.4521. Min Act: -0.1700
Data Index: 7014240 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.4521. Min Act: -0.1700
Data Index: 5743620 (The Pile)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.3583. Min Act: -0.1700
Data Index: 6239402 (The Pile)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.2646. Min Act: -0.1700
Data Index: 8202105 (The Pile)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.5146. Min Act: -0.1700
Data Index: 8544933 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.5771. Min Act: -0.1700
Data Index: 10523360 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.2958. Min Act: -0.1700
Data Index: 9817967 (The Pile)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.2646. Min Act: -0.1700
Data Index: 7008435 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.4208. Min Act: -0.1700
Data Index: 10567427 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.2646. Min Act: -0.1700
Data Index: 981220 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.1708. Min Act: -0.1700
Data Index: 6708077 (The Pile)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.3271. Min Act: -0.1700
Data Index: 5808906 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.3583. Min Act: -0.1700
Data Index: 675010 (The Pile)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.2020. Min Act: -0.1700
Data Index: 1342038 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.5771. Min Act: -0.1700
Data Index: 10603844 (The Pile)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.3271. Min Act: -0.1700
Data Index: 5832226 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7021. Min Range: -4.7021
Max Act: 4.2020. Min Act: -0.1700
Data Index: 1114911 (The Pile)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19