Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1957 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.4802. Min Range: -1.4802
Max Act: 1.4802. Min Act: 0.0001
Data Index: 846877 (The Pile)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4802. Min Range: -1.4802
Max Act: 1.0847. Min Act: 0.0001
Data Index: 126026 (The Pile)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4802. Min Range: -1.4802
Max Act: 1.0662. Min Act: -0.0000
Data Index: 370560 (The Pile)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4802. Min Range: -1.4802
Max Act: 1.0470. Min Act: -0.0000
Data Index: 822618 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4802. Min Range: -1.4802
Max Act: 1.0037. Min Act: 0.0000
Data Index: 1123663 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.9329. Min Act: 0.0000
Data Index: 1483101 (The Pile)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.9307. Min Act: 0.0000
Data Index: 266439 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.9548. Min Act: -0.0000
Data Index: 294432 (The Pile)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.9346. Min Act: 0.0001
Data Index: 911050 (The Pile)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.8938. Min Act: 0.0001
Data Index: 1360120 (The Pile)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.8811. Min Act: 0.0001
Data Index: 1657932 (The Pile)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.8959. Min Act: 0.0000
Data Index: 1673787 (The Pile)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.8764. Min Act: 0.0001
Data Index: 734725 (The Pile)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.8925. Min Act: -0.0000
Data Index: 234444 (The Pile)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.8969. Min Act: 0.0000
Data Index: 1945373 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.9099. Min Act: -0.0000
Data Index: 15450 (The Pile)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.8750. Min Act: 0.0001
Data Index: 1120860 (The Pile)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.8757. Min Act: 0.0000
Data Index: 1942216 (The Pile)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.8130. Min Act: 0.0001
Data Index: 1063466 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4802. Min Range: -1.4802
Max Act: 0.9202. Min Act: -0.0000
Data Index: 1901341 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19