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

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

Neuron 6090 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.6442. Min Act: -0.0000

Data Index: 971747 (C4 (Web Text))

Max Activating Token Index: 981

Text #1

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.5377. Min Act: -0.0000

Data Index: 727652 (C4 (Web Text))

Max Activating Token Index: 469

Text #2

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.5010. Min Act: -0.0000

Data Index: 242086 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.5413. Min Act: -0.0000

Data Index: 829536 (C4 (Web Text))

Max Activating Token Index: 834

Text #4

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.4223. Min Act: -0.0000

Data Index: 1118587 (C4 (Web Text))

Max Activating Token Index: 423

Text #5

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.4174. Min Act: -0.0000

Data Index: 784190 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.3840. Min Act: -0.0000

Data Index: 683476 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.3084. Min Act: -0.0000

Data Index: 1041605 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.2755. Min Act: -0.0000

Data Index: 271964 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.3352. Min Act: -0.0000

Data Index: 143836 (C4 (Web Text))

Max Activating Token Index: 966

Text #10

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.2932. Min Act: -0.0000

Data Index: 741384 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.2951. Min Act: -0.0000

Data Index: 557044 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.2952. Min Act: -0.0000

Data Index: 1207610 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.3127. Min Act: -0.0000

Data Index: 277659 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.2764. Min Act: -0.0000

Data Index: 588879 (C4 (Web Text))

Max Activating Token Index: 273

Text #15

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.2711. Min Act: -0.0000

Data Index: 1204206 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1605391 (Python Code)

Max Activating Token Index: 88

Text #17

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.2639. Min Act: -0.0000

Data Index: 786175 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.2302. Min Act: -0.0000

Data Index: 401084 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.6442. Min Range: -0.6442

Max Act: 0.2236. Min Act: -0.0000

Data Index: 665830 (C4 (Web Text))

Max Activating Token Index: 33