Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2355 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0443. Min Act: -0.0001
Data Index: 144919 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0374. Min Act: -0.0001
Data Index: 1035603 (C4 (Web Text))
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0368. Min Act: -0.0001
Data Index: 967555 (C4 (Web Text))
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0356. Min Act: -0.0001
Data Index: 1594712 (Python Code)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0358. Min Act: -0.0001
Data Index: 180284 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0339. Min Act: -0.0001
Data Index: 1349114 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0351. Min Act: -0.0001
Data Index: 1351245 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0344. Min Act: -0.0001
Data Index: 936641 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0341. Min Act: -0.0001
Data Index: 531003 (C4 (Web Text))
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0330. Min Act: -0.0001
Data Index: 742272 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0349. Min Act: -0.0001
Data Index: 1026021 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0352. Min Act: -0.0001
Data Index: 630940 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0330. Min Act: -0.0001
Data Index: 541675 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0319. Min Act: -0.0001
Data Index: 123650 (C4 (Web Text))
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0330. Min Act: -0.0001
Data Index: 1126126 (C4 (Web Text))
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0305. Min Act: -0.0001
Data Index: 1525815 (Python Code)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0293. Min Act: -0.0001
Data Index: 9322 (C4 (Web Text))
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0300. Min Act: -0.0001
Data Index: 249482 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0313. Min Act: -0.0001
Data Index: 1441730 (Python Code)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0443. Min Range: -0.0443
Max Act: 0.0301. Min Act: -0.0001
Data Index: 1396998 (Python Code)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19