Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2167 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7449. Min Act: -0.0000
Data Index: 1965004 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7565. Min Act: -0.0000
Data Index: 164119 (The Pile)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.8069. Min Act: -0.0000
Data Index: 163917 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7439. Min Act: -0.0000
Data Index: 686125 (The Pile)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7927. Min Act: -0.0000
Data Index: 402844 (The Pile)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7099. Min Act: -0.0000
Data Index: 253763 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7356. Min Act: -0.0000
Data Index: 1089097 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7658. Min Act: -0.0000
Data Index: 82633 (The Pile)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7610. Min Act: -0.0000
Data Index: 130406 (The Pile)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7405. Min Act: -0.0000
Data Index: 1479704 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7421. Min Act: -0.0000
Data Index: 1682457 (The Pile)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7354. Min Act: -0.0000
Data Index: 1750643 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.8319. Min Act: -0.0000
Data Index: 522207 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7675. Min Act: -0.0000
Data Index: 696312 (The Pile)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7577. Min Act: -0.0000
Data Index: 112909 (The Pile)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.6729. Min Act: -0.0000
Data Index: 1140918 (The Pile)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7035. Min Act: -0.0000
Data Index: 74606 (The Pile)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.6621. Min Act: -0.0000
Data Index: 1589965 (The Pile)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.6124. Min Act: -0.0000
Data Index: 1583552 (The Pile)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8319. Min Range: -1.8319
Max Act: 1.7447. Min Act: -0.0000
Data Index: 560502 (The Pile)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19