Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1881 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.0290. Min Range: -2.0290
Max Act: 2.0290. Min Act: -0.0001
Data Index: 1002935 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9180. Min Act: -0.0001
Data Index: 870887 (C4 (Web Text))
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.9752. Min Act: -0.0001
Data Index: 1087518 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.7919. Min Act: -0.0001
Data Index: 105390 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.5977. Min Act: -0.0001
Data Index: 1108168 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.5074. Min Act: -0.0001
Data Index: 1316362 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.7027. Min Act: -0.0001
Data Index: 695253 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.6860. Min Act: -0.0001
Data Index: 576848 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.5716. Min Act: -0.0001
Data Index: 522587 (C4 (Web Text))
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.4846. Min Act: -0.0001
Data Index: 446152 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.6361. Min Act: -0.0001
Data Index: 144799 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.5604. Min Act: -0.0001
Data Index: 670102 (C4 (Web Text))
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.5977. Min Act: -0.0001
Data Index: 860278 (C4 (Web Text))
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.3444. Min Act: -0.0001
Data Index: 997367 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.3951. Min Act: -0.0001
Data Index: 1256409 (C4 (Web Text))
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.4137. Min Act: -0.0001
Data Index: 620648 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.3709. Min Act: -0.0001
Data Index: 38433 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.3585. Min Act: -0.0001
Data Index: 338514 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.2394. Min Act: -0.0001
Data Index: 615375 (C4 (Web Text))
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0290. Min Range: -2.0290
Max Act: 1.2560. Min Act: -0.0001
Data Index: 600805 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19