Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1097 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 3.2686. Min Range: -3.2686
Max Act: 3.2686. Min Act: -0.0000
Data Index: 76355 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.5526. Min Act: -0.0000
Data Index: 990161 (The Pile)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.5839. Min Act: -0.0000
Data Index: 1611726 (The Pile)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.3047. Min Act: -0.0000
Data Index: 1754169 (The Pile)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.4176. Min Act: -0.0000
Data Index: 228460 (The Pile)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.1139. Min Act: -0.0000
Data Index: 1309269 (The Pile)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.3199. Min Act: -0.0000
Data Index: 730177 (The Pile)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.4856. Min Act: -0.0000
Data Index: 1078911 (The Pile)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.0907. Min Act: -0.0000
Data Index: 1452559 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.2938. Min Act: -0.0000
Data Index: 1491046 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2686. Min Range: -3.2686
Max Act: 1.9621. Min Act: 0.0000
Data Index: 89501 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.0751. Min Act: -0.0000
Data Index: 1690217 (The Pile)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.1432. Min Act: -0.0000
Data Index: 648804 (The Pile)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2686. Min Range: -3.2686
Max Act: 1.9425. Min Act: -0.0000
Data Index: 600865 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2686. Min Range: -3.2686
Max Act: 1.9425. Min Act: -0.0000
Data Index: 1815242 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2686. Min Range: -3.2686
Max Act: 1.9425. Min Act: -0.0001
Data Index: 1133006 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2686. Min Range: -3.2686
Max Act: 1.9425. Min Act: -0.0000
Data Index: 321377 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2686. Min Range: -3.2686
Max Act: 1.9425. Min Act: -0.0000
Data Index: 186144 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.1860. Min Act: -0.0000
Data Index: 1324388 (The Pile)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2686. Min Range: -3.2686
Max Act: 2.0140. Min Act: -0.0000
Data Index: 63115 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19