Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3984 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.9195. Min Act: -0.0001
Data Index: 1278677 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.9576. Min Act: -0.0001
Data Index: 1244493 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.8982. Min Act: -0.0001
Data Index: 1049839 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.9781. Min Act: -0.0001
Data Index: 622569 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.8113. Min Act: -0.0001
Data Index: 958848 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.8428. Min Act: -0.0001
Data Index: 980162 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.8496. Min Act: -0.0001
Data Index: 214679 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.8312. Min Act: -0.0001
Data Index: 866767 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.8230. Min Act: -0.0001
Data Index: 224253 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.8457. Min Act: -0.0002
Data Index: 629096 (C4 (Web Text))
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.8410. Min Act: -0.0001
Data Index: 439833 (C4 (Web Text))
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.7873. Min Act: -0.0001
Data Index: 1126184 (C4 (Web Text))
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.7975. Min Act: -0.0001
Data Index: 923006 (C4 (Web Text))
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.8028. Min Act: -0.0001
Data Index: 940452 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.8167. Min Act: -0.0001
Data Index: 82080 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.7905. Min Act: -0.0001
Data Index: 785922 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.8438. Min Act: -0.0001
Data Index: 82402 (C4 (Web Text))
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.7833. Min Act: -0.0001
Data Index: 136798 (C4 (Web Text))
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.7811. Min Act: -0.0001
Data Index: 928678 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9781. Min Range: -0.9781
Max Act: 0.8104. Min Act: -0.0001
Data Index: 719089 (C4 (Web Text))
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #19