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

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

Neuron 4514 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.4054. Min Act: -0.0001

Data Index: 665529 (C4 (Web Text))

Max Activating Token Index: 759

Text #1

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.3530. Min Act: -0.0001

Data Index: 27492 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2896. Min Act: -0.0001

Data Index: 700496 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.3419. Min Act: -0.0001

Data Index: 191925 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.3174. Min Act: -0.0001

Data Index: 1091903 (C4 (Web Text))

Max Activating Token Index: 391

Text #5

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.3519. Min Act: -0.0001

Data Index: 1209200 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.3165. Min Act: -0.0001

Data Index: 756303 (C4 (Web Text))

Max Activating Token Index: 364

Text #7

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.3510. Min Act: -0.0001

Data Index: 1018607 (C4 (Web Text))

Max Activating Token Index: 532

Text #8

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2765. Min Act: -0.0001

Data Index: 542189 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 1.4054. Min Range: -1.4054

Max Act: 1.2343. Min Act: -0.0001

Data Index: 1202702 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9176. Min Act: -0.0000

Data Index: 421094 (C4 (Web Text))

Max Activating Token Index: 107

Text #11

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.9183. Min Act: -0.0001

Data Index: 883806 (C4 (Web Text))

Max Activating Token Index: 117

Text #12

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8863. Min Act: -0.0001

Data Index: 261356 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8565. Min Act: -0.0000

Data Index: 1544201 (Python Code)

Max Activating Token Index: 362

Text #14

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1428366 (Python Code)

Max Activating Token Index: 366

Text #15

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8271. Min Act: -0.0001

Data Index: 1202602 (C4 (Web Text))

Max Activating Token Index: 148

Text #16

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8288. Min Act: -0.0001

Data Index: 289121 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1423881 (Python Code)

Max Activating Token Index: 330

Text #18

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1572390 (Python Code)

Max Activating Token Index: 269

Text #19

Max Range: 1.4054. Min Range: -1.4054

Max Act: 0.7804. Min Act: -0.0001

Data Index: 41025 (C4 (Web Text))

Max Activating Token Index: 227