Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 6022 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.1535. Min Range: -3.1535
Max Act: 3.1535. Min Act: -0.0001
Data Index: 911164 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1535. Min Range: -3.1535
Max Act: 3.0201. Min Act: -0.0001
Data Index: 118921 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.8309. Min Act: -0.0001
Data Index: 472811 (C4 (Web Text))
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.7627. Min Act: -0.0001
Data Index: 825898 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.7118. Min Act: -0.0001
Data Index: 1051833 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.5427. Min Act: -0.0001
Data Index: 1056567 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.3774. Min Act: -0.0001
Data Index: 191856 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.5478. Min Act: -0.0001
Data Index: 459626 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.5573. Min Act: -0.0001
Data Index: 521220 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.4204. Min Act: -0.0001
Data Index: 245733 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.4436. Min Act: -0.0001
Data Index: 1316867 (C4 (Web Text))
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.3050. Min Act: -0.0001
Data Index: 64802 (C4 (Web Text))
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.4017. Min Act: -0.0001
Data Index: 927355 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.2491. Min Act: -0.0001
Data Index: 236239 (C4 (Web Text))
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.3544. Min Act: -0.0001
Data Index: 446708 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.4503. Min Act: -0.0001
Data Index: 717201 (C4 (Web Text))
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.2804. Min Act: -0.0001
Data Index: 667662 (C4 (Web Text))
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.5074. Min Act: -0.0001
Data Index: 252514 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.3861. Min Act: -0.0001
Data Index: 127598 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1535. Min Range: -3.1535
Max Act: 2.3691. Min Act: -0.0001
Data Index: 1116139 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19