Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3393 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.4346. Min Range: -3.4346
Max Act: 3.4346. Min Act: -0.0001
Data Index: 751983 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4346. Min Range: -3.4346
Max Act: 3.0135. Min Act: -0.0001
Data Index: 1207911 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4346. Min Range: -3.4346
Max Act: 2.7046. Min Act: -0.0001
Data Index: 1308465 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4346. Min Range: -3.4346
Max Act: 2.1497. Min Act: -0.0001
Data Index: 329587 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4346. Min Range: -3.4346
Max Act: 2.0816. Min Act: -0.0001
Data Index: 770031 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4346. Min Range: -3.4346
Max Act: 1.7277. Min Act: -0.0001
Data Index: 1083897 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4346. Min Range: -3.4346
Max Act: 1.7363. Min Act: -0.0001
Data Index: 37770 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4346. Min Range: -3.4346
Max Act: 2.0252. Min Act: -0.0001
Data Index: 507651 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4346. Min Range: -3.4346
Max Act: 2.0046. Min Act: -0.0001
Data Index: 292278 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4346. Min Range: -3.4346
Max Act: 1.7581. Min Act: -0.0001
Data Index: 495424 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4346. Min Range: -3.4346
Max Act: 2.0910. Min Act: -0.0001
Data Index: 224411 (C4 (Web Text))
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4346. Min Range: -3.4346
Max Act: 1.9709. Min Act: -0.0001
Data Index: 381551 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4346. Min Range: -3.4346
Max Act: 1.8765. Min Act: -0.0001
Data Index: 760906 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4346. Min Range: -3.4346
Max Act: 1.7288. Min Act: -0.0001
Data Index: 371809 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4346. Min Range: -3.4346
Max Act: 1.8093. Min Act: -0.0001
Data Index: 1260911 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4346. Min Range: -3.4346
Max Act: 1.7685. Min Act: -0.0001
Data Index: 318187 (C4 (Web Text))
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4346. Min Range: -3.4346
Max Act: 1.7266. Min Act: -0.0001
Data Index: 677102 (C4 (Web Text))
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4346. Min Range: -3.4346
Max Act: 1.7609. Min Act: -0.0001
Data Index: 511026 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4346. Min Range: -3.4346
Max Act: 1.7481. Min Act: -0.0001
Data Index: 1124206 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4346. Min Range: -3.4346
Max Act: 1.7036. Min Act: -0.0001
Data Index: 195380 (C4 (Web Text))
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19