Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1291 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.5971. Min Act: -0.0001
Data Index: 351286 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.5094. Min Act: -0.0001
Data Index: 1245689 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.5531. Min Act: -0.0001
Data Index: 1644690 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4345. Min Act: -0.0001
Data Index: 1862549 (The Pile)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.5286. Min Act: -0.0001
Data Index: 612714 (The Pile)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4787. Min Act: -0.0001
Data Index: 929945 (The Pile)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.5253. Min Act: -0.0001
Data Index: 1978433 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4917. Min Act: -0.0001
Data Index: 720508 (The Pile)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4633. Min Act: -0.0001
Data Index: 127771 (The Pile)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4977. Min Act: -0.0001
Data Index: 1530997 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4452. Min Act: -0.0001
Data Index: 513242 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4703. Min Act: -0.0001
Data Index: 1356339 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4469. Min Act: -0.0001
Data Index: 140941 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4652. Min Act: -0.0001
Data Index: 13114 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4870. Min Act: -0.0001
Data Index: 414275 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4148. Min Act: -0.0001
Data Index: 269158 (The Pile)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4577. Min Act: -0.0001
Data Index: 37424 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4234. Min Act: -0.0001
Data Index: 1394748 (The Pile)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4260. Min Act: -0.0001
Data Index: 1398163 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5971. Min Range: -0.5971
Max Act: 0.4238. Min Act: -0.0001
Data Index: 529974 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19