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

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

Neuron 968 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: 0.3895. Min Range: -0.3895

Max Act: 0.3895. Min Act: -0.0001

Data Index: 1124992 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3572. Min Act: -0.0001

Data Index: 893745 (C4 (Web Text))

Max Activating Token Index: 145

Text #2

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3717. Min Act: -0.0001

Data Index: 909548 (C4 (Web Text))

Max Activating Token Index: 272

Text #3

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3307. Min Act: -0.0001

Data Index: 1354535 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3535. Min Act: -0.0001

Data Index: 841411 (C4 (Web Text))

Max Activating Token Index: 511

Text #5

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3350. Min Act: -0.0001

Data Index: 1048276 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3172. Min Act: -0.0001

Data Index: 992853 (C4 (Web Text))

Max Activating Token Index: 127

Text #7

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3610. Min Act: -0.0001

Data Index: 1107390 (C4 (Web Text))

Max Activating Token Index: 152

Text #8

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3276. Min Act: -0.0001

Data Index: 1306085 (C4 (Web Text))

Max Activating Token Index: 602

Text #9

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3333. Min Act: -0.0001

Data Index: 32757 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3168. Min Act: -0.0001

Data Index: 153744 (C4 (Web Text))

Max Activating Token Index: 947

Text #11

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3218. Min Act: -0.0001

Data Index: 744129 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2995. Min Act: -0.0001

Data Index: 1335892 (C4 (Web Text))

Max Activating Token Index: 522

Text #13

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3100. Min Act: -0.0001

Data Index: 1312979 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2735. Min Act: -0.0001

Data Index: 690123 (C4 (Web Text))

Max Activating Token Index: 856

Text #15

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2983. Min Act: -0.0001

Data Index: 355361 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3091. Min Act: -0.0001

Data Index: 1178982 (C4 (Web Text))

Max Activating Token Index: 226

Text #17

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3177. Min Act: -0.0001

Data Index: 736754 (C4 (Web Text))

Max Activating Token Index: 239

Text #18

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.3192. Min Act: -0.0001

Data Index: 200423 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.3895. Min Range: -0.3895

Max Act: 0.2979. Min Act: -0.0001

Data Index: 669417 (C4 (Web Text))

Max Activating Token Index: 627