Model: None
Dataset: The Pile
Neuron 2733 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.5995. Min Act: -0.1700
Data Index: 6666365 (The Pile)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.5526. Min Act: -0.1700
Data Index: 9298081 (The Pile)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.5212. Min Act: -0.1700
Data Index: 2620921 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.5056. Min Act: -0.1700
Data Index: 3115415 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.5056. Min Act: -0.1700
Data Index: 285997 (The Pile)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.4899. Min Act: -0.1700
Data Index: 3751653 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.4899. Min Act: -0.1700
Data Index: 10168457 (The Pile)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.4742. Min Act: -0.1700
Data Index: 3184650 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.4742. Min Act: -0.1700
Data Index: 8687065 (The Pile)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.4429. Min Act: -0.1700
Data Index: 9511800 (The Pile)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.4115. Min Act: -0.1700
Data Index: 8269782 (The Pile)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.4115. Min Act: -0.1700
Data Index: 7751665 (The Pile)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.3958. Min Act: -0.1700
Data Index: 8127060 (The Pile)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.3958. Min Act: -0.1700
Data Index: 6495327 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.3801. Min Act: -0.1700
Data Index: 4715466 (The Pile)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.3801. Min Act: -0.1700
Data Index: 9303030 (The Pile)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.3801. Min Act: -0.1700
Data Index: 8995148 (The Pile)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.3645. Min Act: -0.1700
Data Index: 6732459 (The Pile)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.3645. Min Act: -0.1700
Data Index: 7602774 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5995. Min Range: -3.5995
Max Act: 3.3645. Min Act: -0.1700
Data Index: 6464479 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19