Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3804 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.3447. Min Range: -2.3447
Max Act: 2.3447. Min Act: -0.0001
Data Index: 953984 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3447. Min Range: -2.3447
Max Act: 2.0096. Min Act: -0.0001
Data Index: 1133088 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3447. Min Range: -2.3447
Max Act: 2.0167. Min Act: -0.0001
Data Index: 715230 (C4 (Web Text))
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3447. Min Range: -2.3447
Max Act: 2.0543. Min Act: -0.0001
Data Index: 294502 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3447. Min Range: -2.3447
Max Act: 2.1503. Min Act: -0.0001
Data Index: 585274 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3447. Min Range: -2.3447
Max Act: 2.1632. Min Act: -0.0001
Data Index: 444428 (C4 (Web Text))
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3447. Min Range: -2.3447
Max Act: 2.0330. Min Act: -0.0001
Data Index: 1056270 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3447. Min Range: -2.3447
Max Act: 1.8212. Min Act: -0.0001
Data Index: 685094 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3447. Min Range: -2.3447
Max Act: 1.9323. Min Act: -0.0001
Data Index: 450883 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3447. Min Range: -2.3447
Max Act: 2.0379. Min Act: -0.0001
Data Index: 848342 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3447. Min Range: -2.3447
Max Act: 1.8234. Min Act: -0.0001
Data Index: 430207 (C4 (Web Text))
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3447. Min Range: -2.3447
Max Act: 1.9052. Min Act: -0.0001
Data Index: 1116569 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3447. Min Range: -2.3447
Max Act: 1.9044. Min Act: -0.0001
Data Index: 204202 (C4 (Web Text))
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3447. Min Range: -2.3447
Max Act: 1.8000. Min Act: -0.0001
Data Index: 8415 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3447. Min Range: -2.3447
Max Act: 1.8817. Min Act: -0.0001
Data Index: 427956 (C4 (Web Text))
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3447. Min Range: -2.3447
Max Act: 1.7582. Min Act: -0.0001
Data Index: 827614 (C4 (Web Text))
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3447. Min Range: -2.3447
Max Act: 1.6668. Min Act: -0.0001
Data Index: 1076801 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3447. Min Range: -2.3447
Max Act: 1.8541. Min Act: -0.0001
Data Index: 895056 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3447. Min Range: -2.3447
Max Act: 1.9443. Min Act: -0.0001
Data Index: 779605 (C4 (Web Text))
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3447. Min Range: -2.3447
Max Act: 1.6335. Min Act: -0.0001
Data Index: 1035843 (C4 (Web Text))
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19