Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2932 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.9292. Min Act: -0.0001
Data Index: 208722 (C4 (Web Text))
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.8966. Min Act: -0.0001
Data Index: 367052 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.9800. Min Act: -0.0001
Data Index: 1208100 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.9904. Min Act: -0.0001
Data Index: 971598 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.7135. Min Act: -0.0001
Data Index: 513314 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.8612. Min Act: -0.0001
Data Index: 709930 (C4 (Web Text))
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.8584. Min Act: -0.0001
Data Index: 611606 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.9458. Min Act: -0.0001
Data Index: 387524 (C4 (Web Text))
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.9136. Min Act: -0.0001
Data Index: 740079 (C4 (Web Text))
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.8986. Min Act: -0.0001
Data Index: 1052430 (C4 (Web Text))
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.7692. Min Act: -0.0001
Data Index: 1275196 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.8853. Min Act: -0.0001
Data Index: 1165228 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.8626. Min Act: -0.0001
Data Index: 1288376 (C4 (Web Text))
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.6893. Min Act: -0.0001
Data Index: 1166999 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.6322. Min Act: -0.0001
Data Index: 1349266 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.7069. Min Act: -0.0001
Data Index: 1135276 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.8367. Min Act: -0.0001
Data Index: 1103948 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.8266. Min Act: -0.0001
Data Index: 1338005 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.6601. Min Act: -0.0001
Data Index: 450682 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9904. Min Range: -1.9904
Max Act: 1.7583. Min Act: -0.0001
Data Index: 1263227 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19