Model: None
Dataset: The Pile
Neuron 2863 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6833. Min Act: -0.1700
Data Index: 1261779 (The Pile)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6833. Min Act: -0.1700
Data Index: 6656668 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6520. Min Act: -0.1700
Data Index: 2236359 (The Pile)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6520. Min Act: -0.1700
Data Index: 466664 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6363. Min Act: -0.1700
Data Index: 5410557 (The Pile)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6207. Min Act: -0.1700
Data Index: 153292 (The Pile)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6207. Min Act: -0.1700
Data Index: 788743 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6207. Min Act: -0.1700
Data Index: 7161207 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6207. Min Act: -0.1700
Data Index: 7520174 (The Pile)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6207. Min Act: -0.1700
Data Index: 2748221 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6050. Min Act: -0.1700
Data Index: 9623641 (The Pile)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6050. Min Act: -0.1700
Data Index: 7258526 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.6050. Min Act: -0.1700
Data Index: 5076364 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.5894. Min Act: -0.1700
Data Index: 5622832 (The Pile)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.5894. Min Act: -0.1700
Data Index: 9479897 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.5894. Min Act: -0.1700
Data Index: 7945511 (The Pile)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.5894. Min Act: -0.1700
Data Index: 6237906 (The Pile)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.5894. Min Act: -0.1700
Data Index: 3323928 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.5894. Min Act: -0.1700
Data Index: 3294553 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6833. Min Range: -3.6833
Max Act: 3.5894. Min Act: -0.1700
Data Index: 4498946 (The Pile)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19