Model: None
Dataset: The Pile
Neuron 646 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.4289. Min Act: -0.1700
Data Index: 1917117 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.3351. Min Act: -0.1700
Data Index: 4429989 (The Pile)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.2726. Min Act: -0.1700
Data Index: 10131795 (The Pile)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.2726. Min Act: -0.1700
Data Index: 9061053 (The Pile)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.2101. Min Act: -0.1700
Data Index: 2357539 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.2101. Min Act: -0.1700
Data Index: 1398404 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1788. Min Act: -0.1700
Data Index: 4560908 (The Pile)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1788. Min Act: -0.1700
Data Index: 1818800 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.2101. Min Act: -0.1700
Data Index: 9969062 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1788. Min Act: -0.1700
Data Index: 4153451 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1788. Min Act: -0.1700
Data Index: 6966015 (The Pile)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1788. Min Act: -0.1700
Data Index: 5979898 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1476. Min Act: -0.1700
Data Index: 66809 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1476. Min Act: -0.1700
Data Index: 7978951 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1476. Min Act: -0.1700
Data Index: 2499843 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1476. Min Act: -0.1700
Data Index: 9700733 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1476. Min Act: -0.1700
Data Index: 7472564 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1476. Min Act: -0.1699
Data Index: 3211165 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1476. Min Act: -0.1700
Data Index: 2094148 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4289. Min Range: -4.4289
Max Act: 4.1476. Min Act: -0.1700
Data Index: 506924 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19