Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 956 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.0341. Min Range: -3.0341
Max Act: 3.0341. Min Act: -0.0001
Data Index: 977751 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.8206. Min Act: -0.0001
Data Index: 942954 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.8731. Min Act: -0.0001
Data Index: 1297358 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.6136. Min Act: -0.0001
Data Index: 14027 (C4 (Web Text))
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.5950. Min Act: -0.0001
Data Index: 464105 (C4 (Web Text))
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.4299. Min Act: -0.0001
Data Index: 501848 (C4 (Web Text))
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.5449. Min Act: -0.0001
Data Index: 384375 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.6587. Min Act: -0.0001
Data Index: 42891 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.7964. Min Act: -0.0001
Data Index: 1282735 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.3363. Min Act: -0.0001
Data Index: 642135 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.3254. Min Act: -0.0001
Data Index: 1226402 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.4107. Min Act: -0.0001
Data Index: 896835 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.6852. Min Act: -0.0001
Data Index: 707452 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.7728. Min Act: -0.0001
Data Index: 995570 (C4 (Web Text))
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.7347. Min Act: -0.0001
Data Index: 67207 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.5694. Min Act: -0.0001
Data Index: 239116 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.5658. Min Act: -0.0001
Data Index: 553456 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.3027. Min Act: -0.0001
Data Index: 220422 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.3036. Min Act: -0.0001
Data Index: 1230220 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0341. Min Range: -3.0341
Max Act: 2.4270. Min Act: -0.0001
Data Index: 1114504 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19