Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2604 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.2637. Min Range: -2.2637
Max Act: 2.2637. Min Act: -0.0001
Data Index: 1310367 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.9158. Min Act: -0.0001
Data Index: 1226555 (C4 (Web Text))
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.5855. Min Act: -0.0001
Data Index: 1620399 (Python Code)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.8762. Min Act: -0.0001
Data Index: 1180738 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.7147. Min Act: -0.0001
Data Index: 1464174 (Python Code)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.5484. Min Act: -0.0001
Data Index: 776387 (C4 (Web Text))
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.7258. Min Act: -0.0001
Data Index: 1403382 (Python Code)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.7210. Min Act: -0.0001
Data Index: 1613091 (Python Code)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.6406. Min Act: -0.0001
Data Index: 967334 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.6982. Min Act: -0.0001
Data Index: 1069939 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.5478. Min Act: -0.0001
Data Index: 1061171 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.6342. Min Act: -0.0001
Data Index: 98503 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.5733. Min Act: -0.0001
Data Index: 58056 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.6392. Min Act: -0.0001
Data Index: 1489507 (Python Code)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.5668. Min Act: -0.0001
Data Index: 1634529 (Python Code)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.7978. Min Act: -0.0001
Data Index: 735643 (C4 (Web Text))
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.6318. Min Act: -0.0001
Data Index: 1547405 (Python Code)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.5995. Min Act: -0.0001
Data Index: 1319478 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.7078. Min Act: -0.0001
Data Index: 1510705 (Python Code)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2637. Min Range: -2.2637
Max Act: 1.5439. Min Act: -0.0001
Data Index: 788229 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19