Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2576 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.5149. Min Act: -0.0002
Data Index: 250212 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.4458. Min Act: -0.0002
Data Index: 1073124 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.4553. Min Act: -0.0002
Data Index: 395402 (The Pile)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.4184. Min Act: -0.0002
Data Index: 1598297 (The Pile)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.4246. Min Act: -0.0002
Data Index: 908609 (The Pile)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3908. Min Act: -0.0002
Data Index: 959460 (The Pile)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3851. Min Act: -0.0002
Data Index: 126255 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3894. Min Act: -0.0002
Data Index: 1051102 (The Pile)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3575. Min Act: -0.0002
Data Index: 956256 (The Pile)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3528. Min Act: -0.0002
Data Index: 358306 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3546. Min Act: -0.0002
Data Index: 583507 (The Pile)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3476. Min Act: -0.0002
Data Index: 434535 (The Pile)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3353. Min Act: -0.0002
Data Index: 1783018 (The Pile)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3246. Min Act: -0.0002
Data Index: 495568 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3372. Min Act: -0.0002
Data Index: 929989 (The Pile)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3234. Min Act: -0.0002
Data Index: 126442 (The Pile)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3190. Min Act: -0.0002
Data Index: 770156 (The Pile)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.3051. Min Act: -0.0002
Data Index: 484694 (The Pile)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.2892. Min Act: -0.0002
Data Index: 725727 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5149. Min Range: -0.5149
Max Act: 0.2900. Min Act: -0.0002
Data Index: 234952 (The Pile)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19