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

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

Neuron 1438 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4939. Min Range: -1.4939

Max Act: 1.4939. Min Act: -0.0000

Data Index: 975711 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 1.4939. Min Range: -1.4939

Max Act: 1.0483. Min Act: -0.0000

Data Index: 1352401 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 1.4939. Min Range: -1.4939

Max Act: 1.0651. Min Act: -0.0000

Data Index: 214833 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 1.4939. Min Range: -1.4939

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1180090 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.8934. Min Act: -0.0000

Data Index: 206643 (C4 (Web Text))

Max Activating Token Index: 462

Text #5

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.8830. Min Act: -0.0001

Data Index: 399092 (C4 (Web Text))

Max Activating Token Index: 63

Text #6

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.8987. Min Act: -0.0001

Data Index: 71603 (C4 (Web Text))

Max Activating Token Index: 160

Text #7

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.8698. Min Act: -0.0001

Data Index: 767523 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.8922. Min Act: -0.0000

Data Index: 87430 (C4 (Web Text))

Max Activating Token Index: 842

Text #9

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.8377. Min Act: -0.0000

Data Index: 784790 (C4 (Web Text))

Max Activating Token Index: 124

Text #10

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.8289. Min Act: -0.0000

Data Index: 633187 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.8493. Min Act: -0.0000

Data Index: 1032235 (C4 (Web Text))

Max Activating Token Index: 54

Text #12

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.8193. Min Act: -0.0000

Data Index: 304446 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.8423. Min Act: -0.0000

Data Index: 291666 (C4 (Web Text))

Max Activating Token Index: 690

Text #14

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.7789. Min Act: -0.0001

Data Index: 34532 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.7778. Min Act: -0.0001

Data Index: 781530 (C4 (Web Text))

Max Activating Token Index: 917

Text #16

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.7823. Min Act: -0.0000

Data Index: 772968 (C4 (Web Text))

Max Activating Token Index: 711

Text #17

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.7376. Min Act: -0.0000

Data Index: 429568 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.8247. Min Act: -0.0000

Data Index: 390310 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 1.4939. Min Range: -1.4939

Max Act: 0.7952. Min Act: -0.0000

Data Index: 510309 (C4 (Web Text))

Max Activating Token Index: 254