Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 4 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.0443. Min Range: -1.0443
Max Act: 1.0443. Min Act: -0.0000
Data Index: 667496 (The Pile)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.9463. Min Act: -0.0000
Data Index: 1250417 (The Pile)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.9206. Min Act: -0.0000
Data Index: 764517 (The Pile)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.9393. Min Act: -0.0000
Data Index: 937002 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.9146. Min Act: -0.0000
Data Index: 1224933 (The Pile)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.9060. Min Act: -0.0000
Data Index: 239491 (The Pile)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.8692. Min Act: -0.0000
Data Index: 1650015 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.8395. Min Act: -0.0000
Data Index: 1144576 (The Pile)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.8439. Min Act: -0.0000
Data Index: 373942 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.8131. Min Act: -0.0000
Data Index: 1081131 (The Pile)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.7641. Min Act: -0.0000
Data Index: 333176 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.7877. Min Act: -0.0000
Data Index: 65011 (The Pile)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.8060. Min Act: -0.0000
Data Index: 365946 (The Pile)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.8053. Min Act: -0.0000
Data Index: 1099685 (The Pile)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.8100. Min Act: -0.0000
Data Index: 231101 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.7767. Min Act: -0.0000
Data Index: 1804414 (The Pile)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.7809. Min Act: -0.0000
Data Index: 1743591 (The Pile)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.7636. Min Act: -0.0000
Data Index: 1755431 (The Pile)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.7548. Min Act: -0.0000
Data Index: 967052 (The Pile)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0443. Min Range: -1.0443
Max Act: 0.7282. Min Act: -0.0000
Data Index: 1151093 (The Pile)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19