Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2820 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.4551. Min Range: -3.4551
Max Act: 3.4551. Min Act: -0.0001
Data Index: 622128 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4551. Min Range: -3.4551
Max Act: 3.3635. Min Act: -0.0001
Data Index: 400006 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.8183. Min Act: -0.0000
Data Index: 1299296 (C4 (Web Text))
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.6630. Min Act: -0.0001
Data Index: 445031 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.5923. Min Act: -0.0000
Data Index: 281159 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.6888. Min Act: -0.0001
Data Index: 786802 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.4493. Min Act: -0.0001
Data Index: 536451 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.4184. Min Act: -0.0001
Data Index: 1084775 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.2932. Min Act: -0.0001
Data Index: 855659 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.1232. Min Act: -0.0001
Data Index: 354480 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.2010. Min Act: -0.0000
Data Index: 852974 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.1982. Min Act: -0.0001
Data Index: 939908 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.1762. Min Act: -0.0001
Data Index: 392247 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.1759. Min Act: -0.0001
Data Index: 1335761 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.0409. Min Act: -0.0001
Data Index: 1259038 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.0287. Min Act: -0.0000
Data Index: 327627 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.1181. Min Act: -0.0000
Data Index: 1093376 (C4 (Web Text))
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.0953. Min Act: -0.0001
Data Index: 993096 (C4 (Web Text))
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4551. Min Range: -3.4551
Max Act: 1.8989. Min Act: -0.0001
Data Index: 486475 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4551. Min Range: -3.4551
Max Act: 2.0967. Min Act: -0.0001
Data Index: 1084303 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #19