Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2770 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 2.1761. Min Range: -2.1761
Max Act: 2.1761. Min Act: -0.0001
Data Index: 967840 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1761. Min Range: -2.1761
Max Act: 2.0933. Min Act: -0.0001
Data Index: 1823277 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.9643. Min Act: -0.0001
Data Index: 223214 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.8879. Min Act: -0.0001
Data Index: 693201 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.9080. Min Act: -0.0001
Data Index: 1911487 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.8708. Min Act: -0.0001
Data Index: 1905487 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.8330. Min Act: -0.0001
Data Index: 1471254 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.7472. Min Act: -0.0001
Data Index: 1508799 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.7626. Min Act: -0.0001
Data Index: 76151 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.8214. Min Act: -0.0001
Data Index: 1372447 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.8214. Min Act: -0.0001
Data Index: 1843771 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.7688. Min Act: -0.0001
Data Index: 42795 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.7568. Min Act: -0.0001
Data Index: 1582244 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.6806. Min Act: -0.0001
Data Index: 1649582 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.7736. Min Act: -0.0001
Data Index: 783050 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.7866. Min Act: -0.0001
Data Index: 1855115 (The Pile)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.6985. Min Act: -0.0001
Data Index: 202959 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.6985. Min Act: -0.0001
Data Index: 337547 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.6956. Min Act: -0.0001
Data Index: 922745 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1761. Min Range: -2.1761
Max Act: 1.6226. Min Act: -0.0001
Data Index: 165906 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19