Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2384 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0015. Min Range: -2.0015
Max Act: 2.0015. Min Act: -0.0001
Data Index: 244287 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.8402. Min Act: -0.0001
Data Index: 662046 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.6557. Min Act: -0.0001
Data Index: 942413 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.6480. Min Act: -0.0001
Data Index: 91850 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.6769. Min Act: -0.0001
Data Index: 671063 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.5997. Min Act: -0.0001
Data Index: 526053 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.5658. Min Act: -0.0001
Data Index: 36524 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.4336. Min Act: -0.0001
Data Index: 885637 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.4129. Min Act: -0.0001
Data Index: 522547 (C4 (Web Text))
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.4957. Min Act: -0.0001
Data Index: 132868 (C4 (Web Text))
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.4114. Min Act: -0.0001
Data Index: 277554 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.4029. Min Act: -0.0001
Data Index: 1166029 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.2658. Min Act: -0.0001
Data Index: 1079556 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.3660. Min Act: -0.0001
Data Index: 961041 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.3769. Min Act: -0.0001
Data Index: 935031 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.4398. Min Act: -0.0001
Data Index: 702238 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.3474. Min Act: -0.0001
Data Index: 151607 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.2838. Min Act: -0.0001
Data Index: 1310580 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.3209. Min Act: -0.0001
Data Index: 454411 (C4 (Web Text))
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0015. Min Range: -2.0015
Max Act: 1.1143. Min Act: -0.0001
Data Index: 67376 (C4 (Web Text))
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #19