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

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

Neuron 2260 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: 0.3263. Min Range: -0.3263

Max Act: 0.3263. Min Act: -0.0001

Data Index: 155285 (C4 (Web Text))

Max Activating Token Index: 644

Text #1

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.3139. Min Act: -0.0001

Data Index: 553927 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.3007. Min Act: -0.0001

Data Index: 810453 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2962. Min Act: -0.0001

Data Index: 914905 (C4 (Web Text))

Max Activating Token Index: 730

Text #4

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.3022. Min Act: -0.0001

Data Index: 242545 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2964. Min Act: -0.0001

Data Index: 711507 (C4 (Web Text))

Max Activating Token Index: 925

Text #6

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.3183. Min Act: -0.0001

Data Index: 1185791 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2945. Min Act: -0.0001

Data Index: 421487 (C4 (Web Text))

Max Activating Token Index: 784

Text #8

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2860. Min Act: -0.0001

Data Index: 195411 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2699. Min Act: -0.0001

Data Index: 122498 (C4 (Web Text))

Max Activating Token Index: 576

Text #10

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2641. Min Act: -0.0001

Data Index: 889460 (C4 (Web Text))

Max Activating Token Index: 264

Text #11

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2530. Min Act: -0.0001

Data Index: 1107434 (C4 (Web Text))

Max Activating Token Index: 718

Text #12

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2604. Min Act: -0.0001

Data Index: 1214872 (C4 (Web Text))

Max Activating Token Index: 206

Text #13

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2506. Min Act: -0.0001

Data Index: 111510 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2685. Min Act: -0.0001

Data Index: 1323130 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2497. Min Act: -0.0001

Data Index: 274904 (C4 (Web Text))

Max Activating Token Index: 161

Text #16

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2479. Min Act: -0.0001

Data Index: 248524 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2577. Min Act: -0.0001

Data Index: 662099 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2473. Min Act: -0.0001

Data Index: 492713 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.3263. Min Range: -0.3263

Max Act: 0.2545. Min Act: -0.0001

Data Index: 413193 (C4 (Web Text))

Max Activating Token Index: 32