Model: None
Dataset: The Pile
Neuron 2448 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.9647. Min Act: -0.1700
Data Index: 3465003 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.9647. Min Act: -0.1700
Data Index: 1423293 (The Pile)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.8084. Min Act: -0.1700
Data Index: 9912042 (The Pile)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.7147. Min Act: -0.1700
Data Index: 103958 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.6834. Min Act: -0.1700
Data Index: 4241136 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.6522. Min Act: -0.1700
Data Index: 8866719 (The Pile)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.6209. Min Act: -0.1700
Data Index: 1739973 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.5897. Min Act: -0.1699
Data Index: 9573401 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.5272. Min Act: -0.1700
Data Index: 8320429 (The Pile)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.4647. Min Act: -0.1700
Data Index: 6075010 (The Pile)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.4334. Min Act: -0.1700
Data Index: 10505718 (The Pile)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.4022. Min Act: -0.1700
Data Index: 2051564 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.4022. Min Act: -0.1700
Data Index: 951591 (The Pile)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.3709. Min Act: -0.1700
Data Index: 8264709 (The Pile)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.3397. Min Act: -0.1700
Data Index: 3070657 (The Pile)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.3397. Min Act: -0.1700
Data Index: 9949626 (The Pile)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.3397. Min Act: -0.1700
Data Index: 5878327 (The Pile)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.3084. Min Act: -0.1700
Data Index: 8070432 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.3084. Min Act: -0.1700
Data Index: 6139370 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9647. Min Range: -4.9647
Max Act: 4.2771. Min Act: -0.1700
Data Index: 4700062 (The Pile)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19