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

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

Neuron 908 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.6560. Min Act: -0.0002

Data Index: 41053 (C4 (Web Text))

Max Activating Token Index: 938

Text #1

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.6942. Min Act: -0.0002

Data Index: 1293626 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.6800. Min Act: -0.0002

Data Index: 326672 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.6678. Min Act: -0.0002

Data Index: 28266 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.6002. Min Act: -0.0002

Data Index: 364356 (C4 (Web Text))

Max Activating Token Index: 512

Text #5

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.5404. Min Act: -0.0002

Data Index: 331286 (C4 (Web Text))

Max Activating Token Index: 632

Text #6

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.5787. Min Act: -0.0002

Data Index: 1327943 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.5223. Min Act: -0.0002

Data Index: 861740 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.5435. Min Act: -0.0002

Data Index: 363181 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.5610. Min Act: -0.0002

Data Index: 161342 (C4 (Web Text))

Max Activating Token Index: 323

Text #10

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.5171. Min Act: -0.0002

Data Index: 1294582 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.4877. Min Act: -0.0002

Data Index: 899887 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.5305. Min Act: -0.0002

Data Index: 511329 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.5129. Min Act: -0.0002

Data Index: 182575 (C4 (Web Text))

Max Activating Token Index: 265

Text #14

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.5373. Min Act: -0.0002

Data Index: 297739 (C4 (Web Text))

Max Activating Token Index: 706

Text #15

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.5160. Min Act: -0.0002

Data Index: 1080673 (C4 (Web Text))

Max Activating Token Index: 96

Text #16

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.5337. Min Act: -0.0002

Data Index: 479881 (C4 (Web Text))

Max Activating Token Index: 777

Text #17

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.5104. Min Act: -0.0002

Data Index: 583646 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.4981. Min Act: -0.0002

Data Index: 81813 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 1.6942. Min Range: -1.6942

Max Act: 1.4864. Min Act: -0.0002

Data Index: 1039674 (C4 (Web Text))

Max Activating Token Index: 461