Model: None
Dataset: The Pile
Neuron 826 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.2037. Min Act: -0.1700
Data Index: 8468142 (The Pile)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.1565. Min Act: -0.1700
Data Index: 4121969 (The Pile)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.1722. Min Act: -0.1700
Data Index: 356420 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.1407. Min Act: -0.1700
Data Index: 3973758 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.1722. Min Act: -0.1700
Data Index: 5494940 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.1407. Min Act: -0.1700
Data Index: 8524145 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.1092. Min Act: -0.1700
Data Index: 7621150 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.1092. Min Act: -0.1700
Data Index: 7638245 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.1250. Min Act: -0.1700
Data Index: 5627113 (The Pile)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.1092. Min Act: -0.1700
Data Index: 9269331 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.0934. Min Act: -0.1700
Data Index: 1334371 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.0934. Min Act: -0.1700
Data Index: 9467502 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.0934. Min Act: -0.1700
Data Index: 9301016 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.0934. Min Act: -0.1700
Data Index: 978043 (The Pile)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.0619. Min Act: -0.1700
Data Index: 267197 (The Pile)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.0619. Min Act: -0.1700
Data Index: 8063808 (The Pile)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.0934. Min Act: -0.1700
Data Index: 1067705 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.0777. Min Act: -0.1700
Data Index: 500320 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.0934. Min Act: -0.1700
Data Index: 3059144 (The Pile)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2037. Min Range: -3.2037
Max Act: 3.0777. Min Act: -0.1700
Data Index: 2292263 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19