Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 727 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.5378. Min Act: -0.0001

Data Index: 150236 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.5162. Min Act: -0.0001

Data Index: 416244 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.4452. Min Act: -0.0000

Data Index: 21026 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.3891. Min Act: -0.0001

Data Index: 588880 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.3701. Min Act: -0.0001

Data Index: 953112 (C4 (Web Text))

Max Activating Token Index: 273

Text #5

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.3408. Min Act: -0.0001

Data Index: 415473 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.3136. Min Act: -0.0001

Data Index: 856314 (C4 (Web Text))

Max Activating Token Index: 105

Text #7

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.2985. Min Act: -0.0001

Data Index: 346229 (C4 (Web Text))

Max Activating Token Index: 983

Text #8

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.2947. Min Act: -0.0000

Data Index: 1041003 (C4 (Web Text))

Max Activating Token Index: 683

Text #9

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.2921. Min Act: -0.0000

Data Index: 1183715 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.2718. Min Act: -0.0001

Data Index: 1298804 (C4 (Web Text))

Max Activating Token Index: 543

Text #11

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.3048. Min Act: -0.0001

Data Index: 34195 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.2796. Min Act: -0.0000

Data Index: 469210 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1165608 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.2588. Min Act: -0.0000

Data Index: 132814 (C4 (Web Text))

Max Activating Token Index: 526

Text #15

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.2620. Min Act: -0.0001

Data Index: 1339747 (C4 (Web Text))

Max Activating Token Index: 483

Text #16

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.2513. Min Act: -0.0001

Data Index: 696546 (C4 (Web Text))

Max Activating Token Index: 133

Text #17

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.2437. Min Act: -0.0001

Data Index: 958890 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.2466. Min Act: -0.0001

Data Index: 1304167 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 0.5378. Min Range: -0.5378

Max Act: 0.2323. Min Act: -0.0000

Data Index: 513397 (C4 (Web Text))

Max Activating Token Index: 904