Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2840 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.8890. Min Act: -0.0000
Data Index: 1942244 (The Pile)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.8884. Min Act: -0.0000
Data Index: 1151154 (The Pile)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.6693. Min Act: -0.0000
Data Index: 920508 (The Pile)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.5338. Min Act: -0.0000
Data Index: 324259 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.6919. Min Act: -0.0000
Data Index: 599414 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.5600. Min Act: -0.0000
Data Index: 1839976 (The Pile)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.5366. Min Act: -0.0000
Data Index: 1644333 (The Pile)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.4598. Min Act: -0.0000
Data Index: 143730 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.2291. Min Act: -0.0000
Data Index: 19283 (The Pile)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.4428. Min Act: -0.0000
Data Index: 1099316 (The Pile)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.3293. Min Act: -0.0000
Data Index: 607569 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.3227. Min Act: -0.0000
Data Index: 48544 (The Pile)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.3221. Min Act: -0.0000
Data Index: 1522592 (The Pile)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.4567. Min Act: -0.0000
Data Index: 1256988 (The Pile)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.4386. Min Act: -0.0000
Data Index: 721723 (The Pile)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.3593. Min Act: -0.0000
Data Index: 1058250 (The Pile)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.2850. Min Act: -0.0000
Data Index: 188192 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.3621. Min Act: -0.0000
Data Index: 289593 (The Pile)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.3341. Min Act: -0.0000
Data Index: 1233268 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8890. Min Range: -1.8890
Max Act: 1.3294. Min Act: -0.0000
Data Index: 694682 (The Pile)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19