Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 532 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.4129. Min Act: -0.0001

Data Index: 1179063 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3694. Min Act: -0.0001

Data Index: 525046 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3631. Min Act: -0.0001

Data Index: 516374 (C4 (Web Text))

Max Activating Token Index: 409

Text #3

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3585. Min Act: -0.0001

Data Index: 772965 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3582. Min Act: -0.0001

Data Index: 1090944 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3263. Min Act: -0.0001

Data Index: 412709 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3337. Min Act: -0.0001

Data Index: 62591 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3321. Min Act: -0.0001

Data Index: 1020598 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3055. Min Act: -0.0001

Data Index: 271590 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3142. Min Act: -0.0001

Data Index: 583412 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.2926. Min Act: -0.0001

Data Index: 467146 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3235. Min Act: -0.0001

Data Index: 1147635 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3107. Min Act: -0.0001

Data Index: 963659 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3070. Min Act: -0.0001

Data Index: 1033347 (C4 (Web Text))

Max Activating Token Index: 147

Text #14

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3056. Min Act: -0.0001

Data Index: 606571 (C4 (Web Text))

Max Activating Token Index: 66

Text #15

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3034. Min Act: -0.0001

Data Index: 107362 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3034. Min Act: -0.0001

Data Index: 220244 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.3004. Min Act: -0.0001

Data Index: 432989 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.2969. Min Act: -0.0001

Data Index: 447996 (C4 (Web Text))

Max Activating Token Index: 66

Text #19

Max Range: 0.4129. Min Range: -0.4129

Max Act: 0.2853. Min Act: -0.0001

Data Index: 618177 (C4 (Web Text))

Max Activating Token Index: 555