Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3510 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 3.0592. Min Range: -3.0592
Max Act: 3.0592. Min Act: -0.0001
Data Index: 691296 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.7772. Min Act: -0.0001
Data Index: 274181 (C4 (Web Text))
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.8528. Min Act: -0.0001
Data Index: 634214 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.7077. Min Act: -0.0001
Data Index: 180182 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.4585. Min Act: -0.0001
Data Index: 1264690 (C4 (Web Text))
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.3473. Min Act: -0.0001
Data Index: 1255738 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.4582. Min Act: -0.0001
Data Index: 755920 (C4 (Web Text))
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.3168. Min Act: -0.0001
Data Index: 1302914 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.2824. Min Act: -0.0001
Data Index: 65779 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.3142. Min Act: -0.0001
Data Index: 248574 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.3535. Min Act: -0.0001
Data Index: 1475621 (Python Code)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.1156. Min Act: -0.0001
Data Index: 976425 (C4 (Web Text))
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.2225. Min Act: -0.0001
Data Index: 539772 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.1845. Min Act: -0.0001
Data Index: 143778 (C4 (Web Text))
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.0520. Min Act: -0.0001
Data Index: 398307 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.2659. Min Act: -0.0001
Data Index: 817600 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.1449. Min Act: -0.0001
Data Index: 1260490 (C4 (Web Text))
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.1191. Min Act: -0.0001
Data Index: 339847 (C4 (Web Text))
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0592. Min Range: -3.0592
Max Act: 2.0072. Min Act: -0.0001
Data Index: 1322598 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0592. Min Range: -3.0592
Max Act: 1.9938. Min Act: -0.0001
Data Index: 1320342 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19