Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1256 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.4799. Min Range: -2.4799
Max Act: 2.4799. Min Act: -0.0000
Data Index: 994599 (The Pile)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4799. Min Range: -2.4799
Max Act: 2.3602. Min Act: -0.0000
Data Index: 1190283 (The Pile)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4799. Min Range: -2.4799
Max Act: 2.1636. Min Act: -0.0000
Data Index: 989731 (The Pile)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4799. Min Range: -2.4799
Max Act: 2.1167. Min Act: -0.0000
Data Index: 451824 (The Pile)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.9402. Min Act: -0.0000
Data Index: 990812 (The Pile)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4799. Min Range: -2.4799
Max Act: 2.0160. Min Act: -0.0000
Data Index: 899151 (The Pile)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.8928. Min Act: 0.0000
Data Index: 732571 (The Pile)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.8708. Min Act: 0.0000
Data Index: 1484291 (The Pile)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.7772. Min Act: -0.0000
Data Index: 1393935 (The Pile)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.7757. Min Act: -0.0000
Data Index: 1966413 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.7584. Min Act: -0.0000
Data Index: 212565 (The Pile)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.8718. Min Act: -0.0000
Data Index: 1422933 (The Pile)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.6803. Min Act: -0.0000
Data Index: 1069661 (The Pile)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.7891. Min Act: -0.0000
Data Index: 1391873 (The Pile)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.7399. Min Act: -0.0000
Data Index: 1340965 (The Pile)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.8273. Min Act: -0.0000
Data Index: 869646 (The Pile)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.8146. Min Act: -0.0000
Data Index: 211250 (The Pile)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.8043. Min Act: -0.0000
Data Index: 1295027 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.7904. Min Act: 0.0000
Data Index: 442161 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4799. Min Range: -2.4799
Max Act: 1.6490. Min Act: -0.0000
Data Index: 159214 (The Pile)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19