Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 915 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.4491. Min Act: -0.0001
Data Index: 808509 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.4483. Min Act: -0.0001
Data Index: 601308 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.3798. Min Act: -0.0002
Data Index: 1755863 (The Pile)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.3040. Min Act: -0.0001
Data Index: 295277 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.3097. Min Act: -0.0001
Data Index: 290523 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.3426. Min Act: -0.0001
Data Index: 954644 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.2951. Min Act: -0.0001
Data Index: 1992441 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.2586. Min Act: -0.0001
Data Index: 446703 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.2480. Min Act: -0.0001
Data Index: 1273460 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.2306. Min Act: -0.0001
Data Index: 705830 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.2374. Min Act: -0.0001
Data Index: 1835257 (The Pile)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.2490. Min Act: -0.0001
Data Index: 245526 (The Pile)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.1688. Min Act: -0.0002
Data Index: 181579 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.2362. Min Act: -0.0001
Data Index: 1387389 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.2092. Min Act: -0.0001
Data Index: 851900 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.2106. Min Act: -0.0001
Data Index: 428323 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.2197. Min Act: -0.0001
Data Index: 778098 (The Pile)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.1651. Min Act: -0.0001
Data Index: 1917677 (The Pile)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.1622. Min Act: -0.0001
Data Index: 677214 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4491. Min Range: -1.4491
Max Act: 1.1987. Min Act: -0.0001
Data Index: 417110 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #19