Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2628 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.5208. Min Act: -0.0001
Data Index: 1489333 (Python Code)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.5149. Min Act: -0.0001
Data Index: 357782 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.3775. Min Act: -0.0001
Data Index: 1261352 (C4 (Web Text))
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.4067. Min Act: -0.0001
Data Index: 877244 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.3763. Min Act: -0.0001
Data Index: 949220 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.2675. Min Act: -0.0001
Data Index: 443684 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.2546. Min Act: -0.0001
Data Index: 208671 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.2871. Min Act: -0.0001
Data Index: 1014047 (C4 (Web Text))
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.2462. Min Act: -0.0001
Data Index: 220907 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.2332. Min Act: -0.0001
Data Index: 1042362 (C4 (Web Text))
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.3015. Min Act: -0.0001
Data Index: 411011 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.2476. Min Act: -0.0001
Data Index: 1017854 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.2054. Min Act: -0.0001
Data Index: 535397 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.2496. Min Act: -0.0001
Data Index: 708508 (C4 (Web Text))
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.2823. Min Act: -0.0001
Data Index: 858077 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.1414. Min Act: -0.0001
Data Index: 1572118 (Python Code)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.1960. Min Act: -0.0001
Data Index: 1342178 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.1978. Min Act: -0.0001
Data Index: 496129 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.2233. Min Act: -0.0001
Data Index: 877508 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5208. Min Range: -1.5208
Max Act: 1.2191. Min Act: -0.0001
Data Index: 963391 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19