Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 18 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')
Text #0
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2749. Min Act: -0.0002
Data Index: 1516986 (Python Code)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2459. Min Act: -0.0002
Data Index: 1512405 (Python Code)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2458. Min Act: -0.0001
Data Index: 657660 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2415. Min Act: -0.0001
Data Index: 1471273 (Python Code)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2412. Min Act: -0.0001
Data Index: 1576078 (Python Code)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2399. Min Act: -0.0002
Data Index: 208749 (C4 (Web Text))
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2453. Min Act: -0.0002
Data Index: 1135769 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2379. Min Act: -0.0001
Data Index: 1493306 (Python Code)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2337. Min Act: -0.0002
Data Index: 359818 (C4 (Web Text))
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2420. Min Act: -0.0002
Data Index: 1428810 (Python Code)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2293. Min Act: -0.0002
Data Index: 1542933 (Python Code)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2396. Min Act: -0.0001
Data Index: 197976 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2311. Min Act: 0.0001
Data Index: 226952 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2305. Min Act: -0.0001
Data Index: 572240 (C4 (Web Text))
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2293. Min Act: 0.0001
Data Index: 1514313 (Python Code)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2300. Min Act: -0.0002
Data Index: 1312694 (C4 (Web Text))
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2207. Min Act: -0.0002
Data Index: 695023 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2358. Min Act: -0.0001
Data Index: 1567463 (Python Code)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2277. Min Act: -0.0002
Data Index: 387675 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2749. Min Range: -0.2749
Max Act: 0.2150. Min Act: -0.0002
Data Index: 1160586 (C4 (Web Text))
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19