Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2655 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0563. Min Range: -2.0563
Max Act: 2.0563. Min Act: -0.0001
Data Index: 902873 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.9563. Min Act: -0.0001
Data Index: 655914 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.9534. Min Act: -0.0001
Data Index: 1069890 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.8865. Min Act: -0.0001
Data Index: 874617 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.7415. Min Act: -0.0001
Data Index: 283978 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.7046. Min Act: -0.0001
Data Index: 1237870 (C4 (Web Text))
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.7033. Min Act: -0.0001
Data Index: 1349622 (C4 (Web Text))
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.6833. Min Act: -0.0001
Data Index: 570850 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.5178. Min Act: -0.0001
Data Index: 1329039 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.6596. Min Act: -0.0001
Data Index: 618257 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.4748. Min Act: -0.0001
Data Index: 958358 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.4951. Min Act: -0.0001
Data Index: 1240129 (C4 (Web Text))
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.5116. Min Act: -0.0001
Data Index: 223848 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.6296. Min Act: -0.0001
Data Index: 1103271 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.5140. Min Act: -0.0001
Data Index: 1094121 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.4879. Min Act: -0.0001
Data Index: 128185 (C4 (Web Text))
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.4324. Min Act: -0.0001
Data Index: 498879 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.3540. Min Act: -0.0001
Data Index: 767792 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.4623. Min Act: -0.0001
Data Index: 1315031 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0563. Min Range: -2.0563
Max Act: 1.3575. Min Act: -0.0001
Data Index: 388447 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19