Model: None
Dataset: The Pile
Neuron 3344 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.9026. Min Act: -0.1700
Data Index: 3108269 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.7931. Min Act: -0.1700
Data Index: 8146090 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.7775. Min Act: -0.1700
Data Index: 278007 (The Pile)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.7462. Min Act: -0.1700
Data Index: 10716659 (The Pile)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.7462. Min Act: -0.1700
Data Index: 118465 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.7149. Min Act: -0.1700
Data Index: 1992346 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.7149. Min Act: -0.1700
Data Index: 9529461 (The Pile)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6993. Min Act: -0.1700
Data Index: 131172 (The Pile)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6836. Min Act: -0.1700
Data Index: 5385421 (The Pile)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6836. Min Act: -0.1700
Data Index: 6448750 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6680. Min Act: -0.1700
Data Index: 6745851 (The Pile)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6680. Min Act: -0.1700
Data Index: 4399163 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6523. Min Act: -0.1700
Data Index: 6035844 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6523. Min Act: -0.1700
Data Index: 1315110 (The Pile)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6367. Min Act: -0.1700
Data Index: 6765574 (The Pile)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6367. Min Act: -0.1700
Data Index: 2289833 (The Pile)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6367. Min Act: -0.1700
Data Index: 5923742 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6367. Min Act: -0.1700
Data Index: 3439967 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6210. Min Act: -0.1700
Data Index: 4015903 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9026. Min Range: -3.9026
Max Act: 3.6210. Min Act: -0.1700
Data Index: 4574051 (The Pile)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19