Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4372 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.4369. Min Act: -0.0000

Data Index: 1250133 (C4 (Web Text))

Max Activating Token Index: 528

Text #1

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.4356. Min Act: -0.0000

Data Index: 164227 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.3915. Min Act: -0.0000

Data Index: 1159192 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.3934. Min Act: -0.0000

Data Index: 687500 (C4 (Web Text))

Max Activating Token Index: 493

Text #4

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.3702. Min Act: -0.0000

Data Index: 1127138 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.3832. Min Act: -0.0000

Data Index: 898689 (C4 (Web Text))

Max Activating Token Index: 937

Text #6

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.3261. Min Act: -0.0000

Data Index: 409936 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.3382. Min Act: -0.0000

Data Index: 639457 (C4 (Web Text))

Max Activating Token Index: 401

Text #8

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.3403. Min Act: -0.0000

Data Index: 1616019 (Python Code)

Max Activating Token Index: 271

Text #9

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.3172. Min Act: -0.0000

Data Index: 1423068 (Python Code)

Max Activating Token Index: 546

Text #10

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.2949. Min Act: -0.0000

Data Index: 1132443 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.3273. Min Act: -0.0000

Data Index: 1562148 (Python Code)

Max Activating Token Index: 854

Text #12

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.2991. Min Act: -0.0000

Data Index: 831202 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.3216. Min Act: -0.0000

Data Index: 631183 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.2929. Min Act: -0.0000

Data Index: 1391086 (Python Code)

Max Activating Token Index: 921

Text #15

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.3061. Min Act: -0.0000

Data Index: 360726 (C4 (Web Text))

Max Activating Token Index: 504

Text #16

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.2908. Min Act: -0.0000

Data Index: 985971 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.2907. Min Act: -0.0000

Data Index: 776683 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.2851. Min Act: -0.0000

Data Index: 438394 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.4369. Min Range: -0.4369

Max Act: 0.3050. Min Act: -0.0000

Data Index: 875457 (C4 (Web Text))

Max Activating Token Index: 742