Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3882 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1511. Min Act: -0.0002
Data Index: 645738 (The Pile)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1145. Min Act: -0.0002
Data Index: 293248 (The Pile)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1226. Min Act: -0.0002
Data Index: 1502734 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1222. Min Act: -0.0002
Data Index: 1648069 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1159. Min Act: -0.0002
Data Index: 530414 (The Pile)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1244. Min Act: -0.0002
Data Index: 41069 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1242. Min Act: -0.0002
Data Index: 15305 (The Pile)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1245. Min Act: -0.0002
Data Index: 532001 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1114. Min Act: -0.0002
Data Index: 1412818 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1184. Min Act: -0.0002
Data Index: 223182 (The Pile)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1195. Min Act: -0.0002
Data Index: 453283 (The Pile)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1134. Min Act: -0.0002
Data Index: 1828563 (The Pile)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1168. Min Act: -0.0002
Data Index: 1449487 (The Pile)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1169. Min Act: -0.0002
Data Index: 1309611 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1245. Min Act: -0.0002
Data Index: 1544602 (The Pile)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1218. Min Act: -0.0002
Data Index: 1847378 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1147. Min Act: -0.0002
Data Index: 1576130 (The Pile)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1245. Min Act: -0.0002
Data Index: 366936 (The Pile)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1182. Min Act: -0.0002
Data Index: 634328 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1511. Min Range: -0.1511
Max Act: 0.1139. Min Act: -0.0002
Data Index: 1521590 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19