Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3103 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.7543. Min Act: -0.0001
Data Index: 727351 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.8259. Min Act: -0.0001
Data Index: 135501 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.7585. Min Act: -0.0001
Data Index: 869452 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.5786. Min Act: -0.0001
Data Index: 956402 (C4 (Web Text))
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.4842. Min Act: -0.0001
Data Index: 1164221 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.6316. Min Act: -0.0001
Data Index: 683544 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.6512. Min Act: -0.0001
Data Index: 54916 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.3896. Min Act: -0.0001
Data Index: 1276555 (C4 (Web Text))
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.4750. Min Act: -0.0001
Data Index: 904046 (C4 (Web Text))
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.4415. Min Act: -0.0001
Data Index: 677535 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.4301. Min Act: -0.0001
Data Index: 654391 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.3911. Min Act: -0.0001
Data Index: 1277626 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.4014. Min Act: -0.0001
Data Index: 728122 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.4129. Min Act: -0.0001
Data Index: 1170490 (C4 (Web Text))
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.2677. Min Act: -0.0001
Data Index: 1077995 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.3183. Min Act: -0.0001
Data Index: 1008911 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.2877. Min Act: -0.0001
Data Index: 1161108 (C4 (Web Text))
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.3088. Min Act: -0.0001
Data Index: 277167 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.3351. Min Act: -0.0001
Data Index: 341562 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8259. Min Range: -1.8259
Max Act: 1.1216. Min Act: -0.0001
Data Index: 680670 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #19