Model: None
Dataset: The Pile
Neuron 507 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.8286. Min Act: -0.1700
Data Index: 2835743 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.7817. Min Act: -0.1700
Data Index: 7006276 (The Pile)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.6252. Min Act: -0.1700
Data Index: 10148492 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.6252. Min Act: -0.1700
Data Index: 6843178 (The Pile)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5939. Min Act: -0.1700
Data Index: 10575252 (The Pile)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5939. Min Act: -0.1700
Data Index: 9756237 (The Pile)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5783. Min Act: -0.1700
Data Index: 4546949 (The Pile)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5783. Min Act: -0.1700
Data Index: 2855788 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5626. Min Act: -0.1700
Data Index: 5581867 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5626. Min Act: -0.1700
Data Index: 315031 (The Pile)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5469. Min Act: -0.1700
Data Index: 7612775 (The Pile)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5313. Min Act: -0.1700
Data Index: 6590058 (The Pile)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5313. Min Act: -0.1700
Data Index: 6580751 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5313. Min Act: -0.1700
Data Index: 7037323 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5156. Min Act: -0.1700
Data Index: 8613768 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5156. Min Act: -0.1700
Data Index: 9324863 (The Pile)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.5156. Min Act: -0.1700
Data Index: 230727 (The Pile)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.4999. Min Act: -0.1700
Data Index: 42191 (The Pile)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.4999. Min Act: -0.1700
Data Index: 8456888 (The Pile)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8286. Min Range: -3.8286
Max Act: 3.4999. Min Act: -0.1700
Data Index: 2635845 (The Pile)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #19