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

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

Neuron 2778 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.8472. Min Act: -0.0000

Data Index: 1453730 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.8240. Min Act: -0.0000

Data Index: 1640477 (Python Code)

Max Activating Token Index: 22

Text #2

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.5778. Min Act: -0.0000

Data Index: 1027876 (C4 (Web Text))

Max Activating Token Index: 245

Text #3

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.6053. Min Act: -0.0000

Data Index: 6139 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.5581. Min Act: -0.0000

Data Index: 347285 (C4 (Web Text))

Max Activating Token Index: 186

Text #5

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.6109. Min Act: -0.0000

Data Index: 269482 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.5223. Min Act: -0.0000

Data Index: 1402225 (Python Code)

Max Activating Token Index: 598

Text #7

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.4361. Min Act: -0.0000

Data Index: 1287904 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.5614. Min Act: -0.0000

Data Index: 559068 (C4 (Web Text))

Max Activating Token Index: 485

Text #9

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.4786. Min Act: -0.0000

Data Index: 988087 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.4444. Min Act: -0.0000

Data Index: 1265034 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.4330. Min Act: -0.0000

Data Index: 1023254 (C4 (Web Text))

Max Activating Token Index: 409

Text #12

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.3523. Min Act: -0.0000

Data Index: 19702 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1407745 (Python Code)

Max Activating Token Index: 791

Text #14

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.4318. Min Act: -0.0000

Data Index: 597097 (C4 (Web Text))

Max Activating Token Index: 284

Text #15

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.4087. Min Act: -0.0000

Data Index: 673004 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.3001. Min Act: -0.0000

Data Index: 998845 (C4 (Web Text))

Max Activating Token Index: 92

Text #17

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.2973. Min Act: -0.0000

Data Index: 987407 (C4 (Web Text))

Max Activating Token Index: 723

Text #18

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.3837. Min Act: -0.0000

Data Index: 1233412 (C4 (Web Text))

Max Activating Token Index: 596

Text #19

Max Range: 1.8472. Min Range: -1.8472

Max Act: 1.3947. Min Act: -0.0000

Data Index: 1165852 (C4 (Web Text))

Max Activating Token Index: 886