Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2584 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.2163. Min Act: -0.0001
Data Index: 50416 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1527. Min Act: -0.0001
Data Index: 705094 (C4 (Web Text))
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1724. Min Act: -0.0001
Data Index: 942463 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1727. Min Act: -0.0001
Data Index: 127707 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1256. Min Act: -0.0001
Data Index: 590003 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1464. Min Act: -0.0001
Data Index: 143533 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1605. Min Act: -0.0001
Data Index: 352836 (C4 (Web Text))
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1554. Min Act: -0.0001
Data Index: 499476 (C4 (Web Text))
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1477. Min Act: -0.0001
Data Index: 351758 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1462. Min Act: -0.0001
Data Index: 405893 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1152. Min Act: -0.0001
Data Index: 29727 (C4 (Web Text))
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1310. Min Act: -0.0001
Data Index: 436655 (C4 (Web Text))
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1367. Min Act: -0.0001
Data Index: 9151 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1186. Min Act: -0.0001
Data Index: 299712 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1237. Min Act: -0.0001
Data Index: 750279 (C4 (Web Text))
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1122. Min Act: -0.0001
Data Index: 810287 (C4 (Web Text))
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1246. Min Act: -0.0001
Data Index: 509440 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1198. Min Act: -0.0001
Data Index: 696900 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1195. Min Act: -0.0001
Data Index: 1270544 (C4 (Web Text))
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2163. Min Range: -0.2163
Max Act: 0.1092. Min Act: -0.0001
Data Index: 597712 (C4 (Web Text))
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19