Model: None
Dataset: The Pile
Neuron 4036 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.0696. Min Range: -3.0696
Max Act: 3.0696. Min Act: -0.1700
Data Index: 1690777 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0696. Min Range: -3.0696
Max Act: 3.0222. Min Act: -0.1700
Data Index: 5966362 (The Pile)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9906. Min Act: -0.1700
Data Index: 5872957 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9906. Min Act: -0.1700
Data Index: 7973193 (The Pile)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9748. Min Act: -0.1700
Data Index: 2047592 (The Pile)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9748. Min Act: -0.1700
Data Index: 7422770 (The Pile)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9748. Min Act: -0.1700
Data Index: 2668233 (The Pile)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9589. Min Act: -0.1700
Data Index: 552903 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9589. Min Act: -0.1700
Data Index: 5950711 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9431. Min Act: -0.1700
Data Index: 9453010 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9431. Min Act: -0.1700
Data Index: 8184433 (The Pile)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9431. Min Act: -0.1700
Data Index: 635287 (The Pile)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9431. Min Act: -0.1700
Data Index: 6741628 (The Pile)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9273. Min Act: -0.1700
Data Index: 4650102 (The Pile)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9273. Min Act: -0.1700
Data Index: 4293203 (The Pile)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9114. Min Act: -0.1700
Data Index: 5035636 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9114. Min Act: -0.1700
Data Index: 3413222 (The Pile)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9114. Min Act: -0.1700
Data Index: 6654489 (The Pile)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9114. Min Act: -0.1700
Data Index: 3433410 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0696. Min Range: -3.0696
Max Act: 2.9114. Min Act: -0.1700
Data Index: 1582530 (The Pile)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19