Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4759 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.6485. Min Act: -0.0001
Data Index: 882133 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.6761. Min Act: -0.0001
Data Index: 255392 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.6567. Min Act: -0.0001
Data Index: 318844 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.6897. Min Act: -0.0001
Data Index: 796714 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.6381. Min Act: -0.0001
Data Index: 1294119 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.6279. Min Act: -0.0001
Data Index: 951433 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.5236. Min Act: -0.0001
Data Index: 659050 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.5675. Min Act: -0.0001
Data Index: 1203937 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.5457. Min Act: -0.0001
Data Index: 224097 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.5484. Min Act: -0.0001
Data Index: 968082 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.5788. Min Act: -0.0001
Data Index: 1353351 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.5369. Min Act: -0.0001
Data Index: 238909 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.4549. Min Act: -0.0001
Data Index: 368723 (C4 (Web Text))
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.5619. Min Act: -0.0001
Data Index: 122537 (C4 (Web Text))
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.5683. Min Act: -0.0001
Data Index: 1495146 (Python Code)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.5391. Min Act: -0.0001
Data Index: 1417266 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.4554. Min Act: -0.0001
Data Index: 67057 (C4 (Web Text))
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.5166. Min Act: -0.0001
Data Index: 142681 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.5018. Min Act: -0.0001
Data Index: 566769 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6897. Min Range: -0.6897
Max Act: 0.4677. Min Act: -0.0001
Data Index: 561363 (C4 (Web Text))
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19