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

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

Neuron 1437 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.4465. Min Act: -0.0000

Data Index: 205892 (C4 (Web Text))

Max Activating Token Index: 169

Text #1

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.4040. Min Act: -0.0000

Data Index: 924408 (C4 (Web Text))

Max Activating Token Index: 63

Text #2

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.4096. Min Act: -0.0001

Data Index: 72684 (C4 (Web Text))

Max Activating Token Index: 970

Text #3

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3744. Min Act: -0.0001

Data Index: 1230123 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.4003. Min Act: -0.0001

Data Index: 53859 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3644. Min Act: -0.0000

Data Index: 231432 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3693. Min Act: -0.0001

Data Index: 773974 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3632. Min Act: -0.0001

Data Index: 741498 (C4 (Web Text))

Max Activating Token Index: 468

Text #8

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3352. Min Act: -0.0000

Data Index: 986353 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3208. Min Act: -0.0000

Data Index: 287641 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3025. Min Act: -0.0001

Data Index: 241900 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3466. Min Act: -0.0001

Data Index: 264017 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3229. Min Act: -0.0000

Data Index: 697785 (C4 (Web Text))

Max Activating Token Index: 321

Text #13

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3136. Min Act: -0.0001

Data Index: 513260 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3126. Min Act: -0.0001

Data Index: 787147 (C4 (Web Text))

Max Activating Token Index: 925

Text #15

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3079. Min Act: -0.0001

Data Index: 1279975 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1226282 (C4 (Web Text))

Max Activating Token Index: 334

Text #17

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3104. Min Act: -0.0000

Data Index: 980774 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.3085. Min Act: -0.0001

Data Index: 988339 (C4 (Web Text))

Max Activating Token Index: 40

Text #19

Max Range: 0.4465. Min Range: -0.4465

Max Act: 0.2992. Min Act: -0.0001

Data Index: 823394 (C4 (Web Text))

Max Activating Token Index: 551