Model: None
Dataset: The Pile
Neuron 468 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.4386. Min Act: -0.1700
Data Index: 10361340 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.4223. Min Act: -0.1697
Data Index: 8259250 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3570. Min Act: -0.1700
Data Index: 720975 (The Pile)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3407. Min Act: -0.1700
Data Index: 10684158 (The Pile)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3407. Min Act: -0.1700
Data Index: 9650954 (The Pile)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3407. Min Act: -0.1700
Data Index: 7391946 (The Pile)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3243. Min Act: -0.1700
Data Index: 1654589 (The Pile)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3407. Min Act: -0.1700
Data Index: 6153026 (The Pile)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3243. Min Act: -0.1700
Data Index: 4472015 (The Pile)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3243. Min Act: -0.1700
Data Index: 1106762 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3243. Min Act: -0.1700
Data Index: 9033114 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3243. Min Act: -0.1700
Data Index: 2684614 (The Pile)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3079. Min Act: -0.1700
Data Index: 3099278 (The Pile)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3079. Min Act: -0.1700
Data Index: 6201959 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3079. Min Act: -0.1700
Data Index: 4240467 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3079. Min Act: -0.1700
Data Index: 7600805 (The Pile)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3079. Min Act: -0.1700
Data Index: 1426877 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3079. Min Act: -0.1700
Data Index: 8679320 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.3079. Min Act: -0.1700
Data Index: 8836693 (The Pile)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4386. Min Range: -2.4386
Max Act: 2.2914. Min Act: -0.1700
Data Index: 6887550 (The Pile)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19