Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1940 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.7022. Min Act: -0.0001
Data Index: 127167 (The Pile)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.5198. Min Act: -0.0001
Data Index: 563414 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.5410. Min Act: -0.0001
Data Index: 829658 (The Pile)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.3414. Min Act: -0.0001
Data Index: 331410 (The Pile)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.5190. Min Act: -0.0001
Data Index: 250501 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.4015. Min Act: -0.0001
Data Index: 487831 (The Pile)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.3163. Min Act: -0.0001
Data Index: 1363949 (The Pile)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.3402. Min Act: -0.0001
Data Index: 1791505 (The Pile)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.1516. Min Act: -0.0001
Data Index: 1379155 (The Pile)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.1688. Min Act: -0.0001
Data Index: 66395 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.2475. Min Act: -0.0001
Data Index: 1114607 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.1637. Min Act: -0.0001
Data Index: 637091 (The Pile)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.3112. Min Act: -0.0001
Data Index: 1972813 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.0971. Min Act: -0.0001
Data Index: 1990516 (The Pile)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.0246. Min Act: -0.0001
Data Index: 1239496 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7022. Min Range: -2.7022
Max Act: 1.9687. Min Act: -0.0001
Data Index: 1420783 (The Pile)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7022. Min Range: -2.7022
Max Act: 2.0666. Min Act: -0.0001
Data Index: 736918 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7022. Min Range: -2.7022
Max Act: 1.9860. Min Act: -0.0001
Data Index: 1175909 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7022. Min Range: -2.7022
Max Act: 1.7564. Min Act: -0.0001
Data Index: 654871 (The Pile)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7022. Min Range: -2.7022
Max Act: 1.9722. Min Act: -0.0001
Data Index: 122508 (The Pile)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #19