Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1819 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.8144. Min Act: -0.0000
Data Index: 1660447 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.6885. Min Act: -0.0000
Data Index: 246889 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.5441. Min Act: 0.0000
Data Index: 1821710 (The Pile)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.3480. Min Act: -0.0000
Data Index: 774537 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.4260. Min Act: -0.0000
Data Index: 296657 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.3382. Min Act: -0.0000
Data Index: 79083 (The Pile)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.2556. Min Act: -0.0000
Data Index: 1077413 (The Pile)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.2466. Min Act: -0.0000
Data Index: 1968276 (The Pile)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.2660. Min Act: -0.0000
Data Index: 358669 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.0938. Min Act: -0.0000
Data Index: 1520018 (The Pile)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.1507. Min Act: -0.0000
Data Index: 811789 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.0815. Min Act: 0.0000
Data Index: 514380 (The Pile)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.1161. Min Act: -0.0000
Data Index: 366848 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.1659. Min Act: -0.0000
Data Index: 1441116 (The Pile)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.1041. Min Act: -0.0000
Data Index: 1380353 (The Pile)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.0235. Min Act: -0.0000
Data Index: 1704995 (The Pile)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.2230. Min Act: -0.0000
Data Index: 513968 (The Pile)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.0146. Min Act: -0.0000
Data Index: 980626 (The Pile)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.0582. Min Act: 0.0000
Data Index: 1336050 (The Pile)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8144. Min Range: -1.8144
Max Act: 1.0177. Min Act: -0.0000
Data Index: 1520274 (The Pile)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #19