Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1231 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.2415. Min Act: -0.0001
Data Index: 1169271 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.1618. Min Act: -0.0001
Data Index: 1312450 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.1938. Min Act: -0.0001
Data Index: 1412369 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.1149. Min Act: -0.0001
Data Index: 304821 (The Pile)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.1552. Min Act: -0.0001
Data Index: 138289 (The Pile)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.1085. Min Act: -0.0001
Data Index: 501591 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.1156. Min Act: -0.0001
Data Index: 146097 (The Pile)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.0895. Min Act: -0.0001
Data Index: 1555882 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.0307. Min Act: -0.0001
Data Index: 295072 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2415. Min Range: -1.2415
Max Act: 0.9983. Min Act: -0.0001
Data Index: 1541611 (The Pile)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.0581. Min Act: -0.0001
Data Index: 1898764 (The Pile)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.0225. Min Act: -0.0001
Data Index: 23523 (The Pile)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.0194. Min Act: -0.0001
Data Index: 1208760 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.0037. Min Act: -0.0001
Data Index: 144100 (The Pile)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.0249. Min Act: -0.0001
Data Index: 480385 (The Pile)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2415. Min Range: -1.2415
Max Act: 1.0553. Min Act: -0.0001
Data Index: 1880880 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2415. Min Range: -1.2415
Max Act: 0.9537. Min Act: -0.0001
Data Index: 1914073 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2415. Min Range: -1.2415
Max Act: 0.8735. Min Act: -0.0001
Data Index: 1932198 (The Pile)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2415. Min Range: -1.2415
Max Act: 0.9036. Min Act: -0.0001
Data Index: 1371571 (The Pile)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2415. Min Range: -1.2415
Max Act: 0.9395. Min Act: -0.0001
Data Index: 943429 (The Pile)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19