Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2376 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.0336. Min Range: -3.0336
Max Act: 3.0336. Min Act: -0.0001
Data Index: 798737 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.8938. Min Act: -0.0001
Data Index: 440275 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.8905. Min Act: -0.0001
Data Index: 1316488 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.8868. Min Act: -0.0001
Data Index: 1195283 (C4 (Web Text))
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.5856. Min Act: -0.0001
Data Index: 699562 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.5803. Min Act: -0.0001
Data Index: 342665 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.2822. Min Act: -0.0001
Data Index: 244018 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.6080. Min Act: -0.0001
Data Index: 540299 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.4796. Min Act: -0.0001
Data Index: 1114441 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.4911. Min Act: -0.0001
Data Index: 1264565 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.4458. Min Act: -0.0001
Data Index: 575007 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.1727. Min Act: -0.0001
Data Index: 347094 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.0491. Min Act: -0.0001
Data Index: 514851 (C4 (Web Text))
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.1202. Min Act: -0.0001
Data Index: 186256 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.1044. Min Act: -0.0001
Data Index: 1254103 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.0563. Min Act: -0.0001
Data Index: 53497 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0336. Min Range: -3.0336
Max Act: 1.8409. Min Act: -0.0001
Data Index: 1184 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0336. Min Range: -3.0336
Max Act: 1.9305. Min Act: -0.0001
Data Index: 480743 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0336. Min Range: -3.0336
Max Act: 2.1208. Min Act: -0.0001
Data Index: 398222 (C4 (Web Text))
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0336. Min Range: -3.0336
Max Act: 1.6538. Min Act: -0.0001
Data Index: 36994 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19