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

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

Neuron 2047 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.4204. Min Act: -0.0000

Data Index: 677645 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.4013. Min Act: -0.0000

Data Index: 395000 (C4 (Web Text))

Max Activating Token Index: 772

Text #2

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3398. Min Act: -0.0000

Data Index: 638394 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3554. Min Act: -0.0000

Data Index: 63281 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3335. Min Act: -0.0000

Data Index: 647597 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3346. Min Act: -0.0000

Data Index: 192007 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3218. Min Act: -0.0000

Data Index: 1262117 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3167. Min Act: -0.0000

Data Index: 1310844 (C4 (Web Text))

Max Activating Token Index: 700

Text #8

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3037. Min Act: -0.0000

Data Index: 75229 (C4 (Web Text))

Max Activating Token Index: 845

Text #9

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.3527. Min Act: -0.0000

Data Index: 596692 (C4 (Web Text))

Max Activating Token Index: 964

Text #10

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2906. Min Act: -0.0000

Data Index: 1207121 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1218651 (C4 (Web Text))

Max Activating Token Index: 210

Text #12

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2739. Min Act: -0.0000

Data Index: 145813 (C4 (Web Text))

Max Activating Token Index: 72

Text #13

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2965. Min Act: -0.0000

Data Index: 268154 (C4 (Web Text))

Max Activating Token Index: 90

Text #14

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2559. Min Act: -0.0000

Data Index: 703946 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2626. Min Act: -0.0000

Data Index: 527669 (C4 (Web Text))

Max Activating Token Index: 501

Text #16

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2790. Min Act: -0.0000

Data Index: 512040 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2768. Min Act: -0.0000

Data Index: 1047419 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2764. Min Act: -0.0000

Data Index: 618071 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 0.4204. Min Range: -0.4204

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1306631 (C4 (Web Text))

Max Activating Token Index: 141