Model: None
Dataset: The Pile
Neuron 645 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')
Text #0
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.5189. Min Act: -0.1700
Data Index: 10430168 (The Pile)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.5346. Min Act: -0.1700
Data Index: 7114212 (The Pile)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.4562. Min Act: -0.1700
Data Index: 10334651 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.5189. Min Act: -0.1700
Data Index: 820946 (The Pile)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.4405. Min Act: -0.1700
Data Index: 4912725 (The Pile)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.4249. Min Act: -0.1700
Data Index: 2894826 (The Pile)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.3307. Min Act: -0.1700
Data Index: 4246682 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.3935. Min Act: -0.1700
Data Index: 5074675 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.3621. Min Act: -0.1695
Data Index: 4010682 (The Pile)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.4876. Min Act: -0.1700
Data Index: 5653662 (The Pile)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.3778. Min Act: -0.1693
Data Index: 802119 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.3150. Min Act: -0.1699
Data Index: 7854265 (The Pile)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.3778. Min Act: -0.1695
Data Index: 88450 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.4249. Min Act: -0.1700
Data Index: 3733960 (The Pile)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.4249. Min Act: -0.1698
Data Index: 9592652 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.4249. Min Act: -0.1700
Data Index: 8994931 (The Pile)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.3307. Min Act: -0.1700
Data Index: 7351947 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.1263. Min Act: -0.1699
Data Index: 8866538 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.3464. Min Act: -0.1699
Data Index: 1848629 (The Pile)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5346. Min Range: -3.5346
Max Act: 3.4405. Min Act: -0.1700
Data Index: 2356977 (The Pile)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19