Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2799 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.9489. Min Act: -0.0001
Data Index: 521161 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.9316. Min Act: -0.0001
Data Index: 1956454 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.9308. Min Act: -0.0001
Data Index: 386194 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.8603. Min Act: -0.0001
Data Index: 1096830 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.8554. Min Act: -0.0001
Data Index: 1200956 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.8078. Min Act: -0.0001
Data Index: 1580113 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7901. Min Act: -0.0001
Data Index: 1797244 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7786. Min Act: -0.0001
Data Index: 1599219 (The Pile)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7774. Min Act: -0.0001
Data Index: 1658426 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7508. Min Act: -0.0001
Data Index: 1628434 (The Pile)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7484. Min Act: -0.0001
Data Index: 151092 (The Pile)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7379. Min Act: -0.0001
Data Index: 224326 (The Pile)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7590. Min Act: -0.0001
Data Index: 337060 (The Pile)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7124. Min Act: -0.0001
Data Index: 339928 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7445. Min Act: -0.0001
Data Index: 1852712 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7576. Min Act: -0.0001
Data Index: 1135043 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7219. Min Act: -0.0001
Data Index: 364297 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7068. Min Act: -0.0001
Data Index: 587378 (The Pile)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.7489. Min Act: -0.0001
Data Index: 1545822 (The Pile)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9489. Min Range: -0.9489
Max Act: 0.6703. Min Act: -0.0001
Data Index: 642189 (The Pile)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19