Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3505 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.6639. Min Range: -2.6639
Max Act: 2.6639. Min Act: -0.0000
Data Index: 1192533 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6639. Min Range: -2.6639
Max Act: 2.0593. Min Act: -0.0000
Data Index: 945394 (C4 (Web Text))
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6639. Min Range: -2.6639
Max Act: 2.0353. Min Act: -0.0001
Data Index: 209261 (C4 (Web Text))
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.8886. Min Act: -0.0000
Data Index: 706432 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6639. Min Range: -2.6639
Max Act: 2.0113. Min Act: -0.0001
Data Index: 1348198 (C4 (Web Text))
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.8054. Min Act: -0.0001
Data Index: 643097 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.7514. Min Act: -0.0001
Data Index: 1207753 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.7395. Min Act: -0.0001
Data Index: 1088873 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.8462. Min Act: -0.0000
Data Index: 788646 (C4 (Web Text))
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.7343. Min Act: -0.0001
Data Index: 1236689 (C4 (Web Text))
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.5975. Min Act: -0.0001
Data Index: 547330 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.5788. Min Act: -0.0001
Data Index: 61970 (C4 (Web Text))
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.6731. Min Act: -0.0001
Data Index: 1324078 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.5640. Min Act: -0.0000
Data Index: 477367 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.6152. Min Act: -0.0001
Data Index: 286138 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.5535. Min Act: -0.0001
Data Index: 1015477 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.5162. Min Act: -0.0001
Data Index: 668392 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.5332. Min Act: -0.0001
Data Index: 1219261 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.4749. Min Act: -0.0000
Data Index: 1054854 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6639. Min Range: -2.6639
Max Act: 1.5450. Min Act: -0.0001
Data Index: 876268 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19