Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3202 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.4356. Min Range: -2.4356
Max Act: 2.4356. Min Act: -0.0001
Data Index: 1368834 (Python Code)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4356. Min Range: -2.4356
Max Act: 2.0821. Min Act: -0.0001
Data Index: 1513138 (Python Code)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.8434. Min Act: -0.0001
Data Index: 243893 (C4 (Web Text))
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.7671. Min Act: -0.0001
Data Index: 1605375 (Python Code)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.7441. Min Act: -0.0001
Data Index: 1306643 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.7549. Min Act: -0.0001
Data Index: 1422315 (Python Code)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.6302. Min Act: -0.0001
Data Index: 1518954 (Python Code)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.6643. Min Act: -0.0001
Data Index: 1584165 (Python Code)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.6517. Min Act: -0.0001
Data Index: 1622204 (Python Code)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.6002. Min Act: -0.0000
Data Index: 1602488 (Python Code)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.5975. Min Act: -0.0001
Data Index: 1560258 (Python Code)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.5104. Min Act: -0.0001
Data Index: 893266 (C4 (Web Text))
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.6038. Min Act: -0.0001
Data Index: 1566147 (Python Code)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.6202. Min Act: -0.0001
Data Index: 1225788 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.5174. Min Act: -0.0001
Data Index: 1510752 (Python Code)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.5111. Min Act: -0.0001
Data Index: 1554353 (Python Code)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.5844. Min Act: -0.0001
Data Index: 1414054 (Python Code)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.4544. Min Act: -0.0001
Data Index: 613005 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.3544. Min Act: -0.0001
Data Index: 1349499 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4356. Min Range: -2.4356
Max Act: 1.4017. Min Act: -0.0001
Data Index: 1454265 (Python Code)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19