Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3156 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.2030. Min Range: -2.2030
Max Act: 2.2030. Min Act: -0.0000
Data Index: 378458 (The Pile)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.8143. Min Act: -0.0000
Data Index: 112876 (The Pile)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.8432. Min Act: -0.0000
Data Index: 1530243 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.9173. Min Act: -0.0000
Data Index: 1565569 (The Pile)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.8436. Min Act: -0.0000
Data Index: 155419 (The Pile)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.7367. Min Act: -0.0000
Data Index: 1890891 (The Pile)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.6750. Min Act: -0.0000
Data Index: 757497 (The Pile)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.6552. Min Act: -0.0000
Data Index: 520225 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.3452. Min Act: -0.0000
Data Index: 547486 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.6187. Min Act: -0.0000
Data Index: 1395438 (The Pile)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.6585. Min Act: -0.0000
Data Index: 1340789 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.6374. Min Act: -0.0000
Data Index: 889351 (The Pile)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.5938. Min Act: -0.0000
Data Index: 198350 (The Pile)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.6144. Min Act: -0.0000
Data Index: 1830320 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.4897. Min Act: -0.0000
Data Index: 888279 (The Pile)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.5263. Min Act: -0.0000
Data Index: 1659519 (The Pile)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.5989. Min Act: -0.0000
Data Index: 126308 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.4604. Min Act: -0.0000
Data Index: 329650 (The Pile)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.4450. Min Act: -0.0000
Data Index: 1230783 (The Pile)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2030. Min Range: -2.2030
Max Act: 1.4606. Min Act: -0.0000
Data Index: 105250 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19