Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2648 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.7513. Min Act: -0.0001
Data Index: 274797 (C4 (Web Text))
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.6674. Min Act: -0.0001
Data Index: 1248893 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.6082. Min Act: -0.0001
Data Index: 580695 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.6580. Min Act: -0.0001
Data Index: 147501 (C4 (Web Text))
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.6229. Min Act: -0.0001
Data Index: 151738 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.6271. Min Act: -0.0001
Data Index: 447466 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.6399. Min Act: -0.0001
Data Index: 153577 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.5699. Min Act: -0.0001
Data Index: 251079 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.6162. Min Act: -0.0001
Data Index: 1227709 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.5687. Min Act: -0.0001
Data Index: 216055 (C4 (Web Text))
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.6019. Min Act: -0.0001
Data Index: 338018 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.5771. Min Act: -0.0001
Data Index: 881351 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.5830. Min Act: -0.0001
Data Index: 298330 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.5822. Min Act: -0.0001
Data Index: 206062 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.5623. Min Act: -0.0001
Data Index: 1145898 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.5962. Min Act: -0.0001
Data Index: 192203 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.5595. Min Act: -0.0001
Data Index: 218875 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.5659. Min Act: -0.0001
Data Index: 445165 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.5461. Min Act: -0.0001
Data Index: 1325328 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7513. Min Range: -0.7513
Max Act: 0.5269. Min Act: -0.0001
Data Index: 97197 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19