Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1442 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.5496. Min Act: -0.0001
Data Index: 1825374 (The Pile)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.4968. Min Act: -0.0001
Data Index: 9981 (The Pile)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.5388. Min Act: -0.0001
Data Index: 1968209 (The Pile)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.4357. Min Act: -0.0001
Data Index: 1290984 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.4628. Min Act: -0.0001
Data Index: 955620 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.4618. Min Act: -0.0001
Data Index: 1577156 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.5420. Min Act: -0.0001
Data Index: 143602 (The Pile)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.3745. Min Act: -0.0001
Data Index: 549991 (The Pile)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.3804. Min Act: -0.0001
Data Index: 1550813 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.4225. Min Act: -0.0001
Data Index: 847984 (The Pile)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.3260. Min Act: -0.0001
Data Index: 1221929 (The Pile)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.3991. Min Act: -0.0001
Data Index: 1540285 (The Pile)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.4350. Min Act: -0.0001
Data Index: 738302 (The Pile)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.3499. Min Act: -0.0001
Data Index: 1794425 (The Pile)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.4443. Min Act: -0.0001
Data Index: 1607921 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.3264. Min Act: -0.0001
Data Index: 889446 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.3489. Min Act: -0.0001
Data Index: 1507193 (The Pile)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.3276. Min Act: -0.0001
Data Index: 1415824 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.4982. Min Act: -0.0001
Data Index: 534074 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5496. Min Range: -1.5496
Max Act: 1.2808. Min Act: -0.0001
Data Index: 1815928 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19