Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 38 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.6397. Min Act: -0.0001
Data Index: 530788 (The Pile)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.5062. Min Act: -0.0001
Data Index: 384446 (The Pile)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.4571. Min Act: -0.0001
Data Index: 718591 (The Pile)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.3638. Min Act: -0.0001
Data Index: 631489 (The Pile)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.3780. Min Act: -0.0001
Data Index: 1299783 (The Pile)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.3187. Min Act: -0.0001
Data Index: 1503944 (The Pile)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.2515. Min Act: -0.0001
Data Index: 252541 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.2200. Min Act: -0.0001
Data Index: 1667551 (The Pile)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.3004. Min Act: -0.0001
Data Index: 954832 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.2284. Min Act: -0.0001
Data Index: 1220819 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.2427. Min Act: -0.0001
Data Index: 1682362 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.2364. Min Act: -0.0001
Data Index: 28300 (The Pile)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.1869. Min Act: -0.0001
Data Index: 413998 (The Pile)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.2206. Min Act: -0.0001
Data Index: 80582 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.2059. Min Act: -0.0001
Data Index: 154624 (The Pile)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.1581. Min Act: -0.0001
Data Index: 652466 (The Pile)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.1929. Min Act: -0.0001
Data Index: 221942 (The Pile)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.0853. Min Act: -0.0001
Data Index: 1256663 (The Pile)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.1162. Min Act: -0.0001
Data Index: 1126432 (The Pile)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6397. Min Range: -1.6397
Max Act: 1.1852. Min Act: -0.0001
Data Index: 1572724 (The Pile)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19