Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2892 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.1779. Min Range: -3.1779
Max Act: 3.1779. Min Act: -0.0001
Data Index: 1277571 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.6999. Min Act: -0.0001
Data Index: 482693 (C4 (Web Text))
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.9488. Min Act: -0.0001
Data Index: 334260 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.9130. Min Act: -0.0001
Data Index: 143706 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.7227. Min Act: -0.0001
Data Index: 525202 (C4 (Web Text))
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.6859. Min Act: -0.0001
Data Index: 363973 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.6398. Min Act: -0.0001
Data Index: 835056 (C4 (Web Text))
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.6083. Min Act: -0.0001
Data Index: 711796 (C4 (Web Text))
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.4666. Min Act: -0.0001
Data Index: 241662 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.2994. Min Act: -0.0001
Data Index: 307002 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.3352. Min Act: -0.0001
Data Index: 884803 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.3417. Min Act: -0.0001
Data Index: 665373 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.4303. Min Act: -0.0001
Data Index: 517391 (C4 (Web Text))
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.2710. Min Act: -0.0001
Data Index: 785140 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.2629. Min Act: -0.0001
Data Index: 734226 (C4 (Web Text))
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.3599. Min Act: -0.0001
Data Index: 544785 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.1139. Min Act: -0.0001
Data Index: 1132416 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.1978. Min Act: -0.0001
Data Index: 53186 (C4 (Web Text))
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.3365. Min Act: -0.0001
Data Index: 543887 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1779. Min Range: -3.1779
Max Act: 2.3155. Min Act: -0.0001
Data Index: 607303 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19