Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1627 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.1124. Min Range: -1.1124
Max Act: 1.0601. Min Act: 0.0000
Data Index: 1964656 (The Pile)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1124. Min Range: -1.1124
Max Act: 1.0693. Min Act: -0.0000
Data Index: 322844 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1124. Min Range: -1.1124
Max Act: 1.1124. Min Act: -0.0000
Data Index: 412385 (The Pile)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1124. Min Range: -1.1124
Max Act: 1.0102. Min Act: -0.0000
Data Index: 187256 (The Pile)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.8956. Min Act: 0.0000
Data Index: 801835 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.8954. Min Act: -0.0000
Data Index: 1214132 (The Pile)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.9471. Min Act: 0.0000
Data Index: 919813 (The Pile)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.9202. Min Act: -0.0000
Data Index: 1930081 (The Pile)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.9424. Min Act: -0.0000
Data Index: 1437680 (The Pile)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.9370. Min Act: -0.0000
Data Index: 265820 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.8686. Min Act: -0.0000
Data Index: 1946097 (The Pile)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.9228. Min Act: -0.0000
Data Index: 1934045 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.9178. Min Act: -0.0000
Data Index: 704050 (The Pile)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.8889. Min Act: -0.0000
Data Index: 11015 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.8500. Min Act: -0.0000
Data Index: 1207804 (The Pile)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.8836. Min Act: 0.0000
Data Index: 855239 (The Pile)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.8562. Min Act: -0.0000
Data Index: 498573 (The Pile)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.8757. Min Act: -0.0000
Data Index: 1318223 (The Pile)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.8524. Min Act: -0.0000
Data Index: 1007274 (The Pile)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1124. Min Range: -1.1124
Max Act: 0.8777. Min Act: 0.0000
Data Index: 1714645 (The Pile)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19