Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2206 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.4843. Min Act: -0.0001
Data Index: 1938397 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.2509. Min Act: -0.0001
Data Index: 817641 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.3577. Min Act: -0.0001
Data Index: 1382030 (The Pile)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.3513. Min Act: -0.0001
Data Index: 685041 (The Pile)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.2769. Min Act: -0.0001
Data Index: 661542 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.3131. Min Act: -0.0001
Data Index: 1991948 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.2161. Min Act: -0.0001
Data Index: 62407 (The Pile)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.3497. Min Act: -0.0001
Data Index: 328518 (The Pile)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.1614. Min Act: -0.0001
Data Index: 496136 (The Pile)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.2071. Min Act: -0.0001
Data Index: 1118651 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.2061. Min Act: -0.0001
Data Index: 1912852 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.1357. Min Act: -0.0001
Data Index: 1705023 (The Pile)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.0881. Min Act: -0.0001
Data Index: 320021 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.0808. Min Act: -0.0001
Data Index: 528729 (The Pile)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.1245. Min Act: -0.0001
Data Index: 11547 (The Pile)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.1128. Min Act: -0.0001
Data Index: 610675 (The Pile)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.1138. Min Act: -0.0001
Data Index: 299847 (The Pile)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.1364. Min Act: -0.0001
Data Index: 241786 (The Pile)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.0657. Min Act: -0.0001
Data Index: 1164980 (The Pile)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4843. Min Range: -1.4843
Max Act: 1.1656. Min Act: -0.0001
Data Index: 1231925 (The Pile)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19