Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 450 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.9361. Min Act: -0.0001
Data Index: 424747 (The Pile)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.8828. Min Act: -0.0001
Data Index: 334346 (The Pile)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.8758. Min Act: -0.0001
Data Index: 654640 (The Pile)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.8439. Min Act: -0.0001
Data Index: 996882 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.8273. Min Act: -0.0000
Data Index: 675469 (The Pile)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.8229. Min Act: -0.0001
Data Index: 1796033 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.8142. Min Act: -0.0001
Data Index: 1221039 (The Pile)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.8183. Min Act: -0.0001
Data Index: 641704 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.7732. Min Act: -0.0001
Data Index: 107554 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.8257. Min Act: -0.0001
Data Index: 514956 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.8190. Min Act: -0.0001
Data Index: 1636847 (The Pile)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.8298. Min Act: -0.0001
Data Index: 1852956 (The Pile)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.8254. Min Act: -0.0001
Data Index: 220487 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.7674. Min Act: -0.0001
Data Index: 1541231 (The Pile)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.7414. Min Act: -0.0001
Data Index: 1267326 (The Pile)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.7604. Min Act: -0.0001
Data Index: 482748 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.7054. Min Act: -0.0001
Data Index: 1944319 (The Pile)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.8184. Min Act: -0.0000
Data Index: 197658 (The Pile)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.7391. Min Act: -0.0001
Data Index: 51602 (The Pile)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9361. Min Range: -0.9361
Max Act: 0.7584. Min Act: -0.0001
Data Index: 1497516 (The Pile)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #19