Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2269 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.8206. Min Act: -0.0002
Data Index: 222298 (C4 (Web Text))
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.5387. Min Act: -0.0001
Data Index: 1164191 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.6051. Min Act: -0.0002
Data Index: 1018421 (C4 (Web Text))
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.6881. Min Act: -0.0001
Data Index: 1210848 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.7308. Min Act: -0.0001
Data Index: 649216 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.4407. Min Act: -0.0002
Data Index: 1052236 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.5437. Min Act: -0.0001
Data Index: 681032 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.5769. Min Act: -0.0002
Data Index: 996901 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.5058. Min Act: -0.0001
Data Index: 321176 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.5094. Min Act: -0.0001
Data Index: 104389 (C4 (Web Text))
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.5194. Min Act: -0.0002
Data Index: 1058382 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.2704. Min Act: -0.0001
Data Index: 293693 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.2911. Min Act: -0.0001
Data Index: 380103 (C4 (Web Text))
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.3653. Min Act: -0.0001
Data Index: 291976 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.3524. Min Act: -0.0001
Data Index: 1052660 (C4 (Web Text))
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.3525. Min Act: -0.0002
Data Index: 1205742 (C4 (Web Text))
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.3459. Min Act: -0.0002
Data Index: 270741 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.4080. Min Act: -0.0002
Data Index: 423741 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.3101. Min Act: -0.0002
Data Index: 648428 (C4 (Web Text))
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8206. Min Range: -1.8206
Max Act: 1.2798. Min Act: -0.0001
Data Index: 1438758 (Python Code)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #19