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

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

Neuron 1749 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.3347. Min Act: -0.0001

Data Index: 13442 (C4 (Web Text))

Max Activating Token Index: 139

Text #1

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2707. Min Act: -0.0001

Data Index: 171956 (C4 (Web Text))

Max Activating Token Index: 773

Text #2

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2546. Min Act: -0.0001

Data Index: 1074734 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2639. Min Act: -0.0001

Data Index: 558767 (C4 (Web Text))

Max Activating Token Index: 258

Text #4

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2614. Min Act: -0.0001

Data Index: 102281 (C4 (Web Text))

Max Activating Token Index: 232

Text #5

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2533. Min Act: -0.0001

Data Index: 749001 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2241. Min Act: -0.0001

Data Index: 561844 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2288. Min Act: -0.0001

Data Index: 356224 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2120. Min Act: -0.0001

Data Index: 293278 (C4 (Web Text))

Max Activating Token Index: 681

Text #9

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2259. Min Act: -0.0001

Data Index: 2553 (C4 (Web Text))

Max Activating Token Index: 372

Text #10

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2205. Min Act: -0.0001

Data Index: 995059 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2188. Min Act: -0.0001

Data Index: 425873 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.1875. Min Act: -0.0001

Data Index: 520537 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2101. Min Act: -0.0001

Data Index: 789621 (C4 (Web Text))

Max Activating Token Index: 129

Text #14

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.1939. Min Act: -0.0001

Data Index: 284510 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.1945. Min Act: -0.0001

Data Index: 909398 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.2022. Min Act: -0.0001

Data Index: 1053953 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.1984. Min Act: -0.0001

Data Index: 491076 (C4 (Web Text))

Max Activating Token Index: 133

Text #18

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.1980. Min Act: -0.0001

Data Index: 200945 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.3347. Min Range: -0.3347

Max Act: 0.1969. Min Act: -0.0001

Data Index: 1124592 (C4 (Web Text))

Max Activating Token Index: 575