Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 975 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.9387. Min Act: -0.0001
Data Index: 98137 (The Pile)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.9484. Min Act: -0.0001
Data Index: 1085088 (The Pile)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.9603. Min Act: -0.0001
Data Index: 235154 (The Pile)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.9609. Min Act: -0.0001
Data Index: 1444603 (The Pile)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.9099. Min Act: -0.0001
Data Index: 1129264 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.9108. Min Act: -0.0001
Data Index: 551677 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8895. Min Act: -0.0001
Data Index: 1461361 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.9500. Min Act: -0.0001
Data Index: 1479132 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8848. Min Act: -0.0001
Data Index: 296907 (The Pile)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8568. Min Act: -0.0001
Data Index: 1119122 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8888. Min Act: -0.0001
Data Index: 1190993 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8986. Min Act: -0.0001
Data Index: 1866308 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8433. Min Act: -0.0001
Data Index: 262784 (The Pile)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8473. Min Act: -0.0001
Data Index: 1261524 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8345. Min Act: -0.0001
Data Index: 1825132 (The Pile)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8413. Min Act: -0.0001
Data Index: 1122888 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8759. Min Act: -0.0001
Data Index: 359711 (The Pile)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8194. Min Act: -0.0001
Data Index: 803129 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8283. Min Act: -0.0001
Data Index: 1610544 (The Pile)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9609. Min Range: -0.9609
Max Act: 0.8450. Min Act: -0.0001
Data Index: 69145 (The Pile)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19