Model: None
Dataset: The Pile
Neuron 1431 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.3330. Min Act: -0.1700
Data Index: 5766677 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.2859. Min Act: -0.1700
Data Index: 3599805 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.2230. Min Act: -0.1700
Data Index: 4598973 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.2230. Min Act: -0.1700
Data Index: 9621618 (The Pile)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.2073. Min Act: -0.1700
Data Index: 5601706 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.2073. Min Act: -0.1700
Data Index: 1236034 (The Pile)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1916. Min Act: -0.1700
Data Index: 1705228 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1758. Min Act: -0.1700
Data Index: 4444897 (The Pile)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1758. Min Act: -0.1700
Data Index: 7474464 (The Pile)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1601. Min Act: -0.1700
Data Index: 5716016 (The Pile)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1601. Min Act: -0.1700
Data Index: 4410875 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1601. Min Act: -0.1700
Data Index: 5908471 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1601. Min Act: -0.1700
Data Index: 476656 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1443. Min Act: -0.1700
Data Index: 4486390 (The Pile)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1286. Min Act: -0.1700
Data Index: 55106 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1286. Min Act: -0.1700
Data Index: 2366527 (The Pile)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1286. Min Act: -0.1700
Data Index: 6606000 (The Pile)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1286. Min Act: -0.1700
Data Index: 4627010 (The Pile)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1286. Min Act: -0.1700
Data Index: 5721274 (The Pile)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3330. Min Range: -3.3330
Max Act: 3.1286. Min Act: -0.1700
Data Index: 4748224 (The Pile)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19