Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2563 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.3282. Min Act: -0.0001
Data Index: 5994 (The Pile)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.4596. Min Act: -0.0001
Data Index: 1795760 (The Pile)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.4844. Min Act: -0.0001
Data Index: 1425674 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.5167. Min Act: -0.0001
Data Index: 993859 (The Pile)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.2896. Min Act: -0.0001
Data Index: 358533 (The Pile)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.3144. Min Act: -0.0001
Data Index: 1235499 (The Pile)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.2734. Min Act: -0.0001
Data Index: 1864643 (The Pile)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.2229. Min Act: -0.0001
Data Index: 1575602 (The Pile)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.1205. Min Act: -0.0001
Data Index: 554469 (The Pile)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.1756. Min Act: -0.0001
Data Index: 1193815 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.1510. Min Act: -0.0001
Data Index: 1625839 (The Pile)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.1118. Min Act: -0.0001
Data Index: 367275 (The Pile)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.2409. Min Act: -0.0001
Data Index: 170206 (The Pile)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.1963. Min Act: -0.0001
Data Index: 1796754 (The Pile)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.0215. Min Act: -0.0001
Data Index: 1513771 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.1356. Min Act: -0.0001
Data Index: 3590 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.1532. Min Act: -0.0001
Data Index: 510131 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.1567. Min Act: -0.0001
Data Index: 782042 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.0454. Min Act: -0.0001
Data Index: 387876 (The Pile)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5167. Min Range: -1.5167
Max Act: 1.1565. Min Act: -0.0001
Data Index: 1653439 (The Pile)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19