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

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

Neuron 2710 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2965. Min Act: 0.0000

Data Index: 59109 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2708. Min Act: -0.0000

Data Index: 550383 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2802. Min Act: -0.0000

Data Index: 489219 (C4 (Web Text))

Max Activating Token Index: 429

Text #3

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2635. Min Act: -0.0000

Data Index: 1046483 (C4 (Web Text))

Max Activating Token Index: 181

Text #4

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2532. Min Act: -0.0000

Data Index: 734081 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2553. Min Act: 0.0000

Data Index: 288175 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2596. Min Act: -0.0000

Data Index: 931759 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1310989 (C4 (Web Text))

Max Activating Token Index: 960

Text #8

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2484. Min Act: -0.0000

Data Index: 28590 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2466. Min Act: -0.0000

Data Index: 266390 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2469. Min Act: -0.0000

Data Index: 883752 (C4 (Web Text))

Max Activating Token Index: 510

Text #11

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1087218 (C4 (Web Text))

Max Activating Token Index: 330

Text #12

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2293. Min Act: -0.0000

Data Index: 880806 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2335. Min Act: -0.0000

Data Index: 621360 (C4 (Web Text))

Max Activating Token Index: 333

Text #14

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2269. Min Act: -0.0000

Data Index: 661652 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2154. Min Act: -0.0000

Data Index: 805446 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1104533 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2078. Min Act: -0.0000

Data Index: 336981 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2076. Min Act: -0.0000

Data Index: 136973 (C4 (Web Text))

Max Activating Token Index: 924

Text #19

Max Range: 0.2965. Min Range: -0.2965

Max Act: 0.2199. Min Act: -0.0000

Data Index: 317864 (C4 (Web Text))

Max Activating Token Index: 203