Model: None
Dataset: The Pile
Neuron 2567 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.4409. Min Act: -0.1700
Data Index: 8960214 (The Pile)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.4409. Min Act: -0.1700
Data Index: 8588473 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.3159. Min Act: -0.1700
Data Index: 10467490 (The Pile)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.2847. Min Act: -0.1700
Data Index: 9554600 (The Pile)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.2222. Min Act: -0.1700
Data Index: 8307950 (The Pile)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.1909. Min Act: -0.1700
Data Index: 8122953 (The Pile)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.1909. Min Act: -0.1699
Data Index: 6412313 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.1909. Min Act: -0.1700
Data Index: 4714153 (The Pile)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.1597. Min Act: -0.1700
Data Index: 8696587 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.1597. Min Act: -0.1698
Data Index: 892767 (The Pile)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.1284. Min Act: -0.1700
Data Index: 2909518 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.1284. Min Act: -0.1700
Data Index: 506374 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.1284. Min Act: -0.1699
Data Index: 9377973 (The Pile)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.0972. Min Act: -0.1700
Data Index: 1176583 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.0972. Min Act: -0.1700
Data Index: 9552472 (The Pile)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.0972. Min Act: -0.1700
Data Index: 4712864 (The Pile)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.0347. Min Act: -0.1700
Data Index: 4861544 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.0347. Min Act: -0.1700
Data Index: 507504 (The Pile)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.0034. Min Act: -0.1700
Data Index: 1246297 (The Pile)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4409. Min Range: -7.4409
Max Act: 7.0034. Min Act: -0.1700
Data Index: 8991848 (The Pile)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19