Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3764 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1816. Min Act: -0.0001
Data Index: 777341 (C4 (Web Text))
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1427. Min Act: -0.0001
Data Index: 668487 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1322. Min Act: -0.0001
Data Index: 576406 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1395. Min Act: -0.0001
Data Index: 734271 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1257. Min Act: -0.0001
Data Index: 837954 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1327. Min Act: -0.0001
Data Index: 312065 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1200. Min Act: -0.0001
Data Index: 1276327 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1210. Min Act: -0.0001
Data Index: 454949 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1255. Min Act: -0.0001
Data Index: 1022652 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1157. Min Act: -0.0001
Data Index: 157999 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1130. Min Act: -0.0001
Data Index: 1111066 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1074. Min Act: -0.0001
Data Index: 1129616 (C4 (Web Text))
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1293. Min Act: -0.0001
Data Index: 445226 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1190. Min Act: -0.0001
Data Index: 1341178 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1108. Min Act: -0.0001
Data Index: 696776 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1411. Min Act: -0.0001
Data Index: 933337 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1132. Min Act: -0.0001
Data Index: 597038 (C4 (Web Text))
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.0995. Min Act: -0.0001
Data Index: 646118 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1216. Min Act: -0.0001
Data Index: 1208269 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1816. Min Range: -0.1816
Max Act: 0.1038. Min Act: -0.0001
Data Index: 584085 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #19