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

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

Neuron 515 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: 1.9010. Min Range: -1.9010

Max Act: 1.9010. Min Act: -0.0001

Data Index: 147369 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.8184. Min Act: -0.0001

Data Index: 331473 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.6578. Min Act: -0.0000

Data Index: 425749 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.4689. Min Act: -0.0001

Data Index: 1312500 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.6785. Min Act: -0.0001

Data Index: 1113373 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.5120. Min Act: -0.0001

Data Index: 1327294 (C4 (Web Text))

Max Activating Token Index: 158

Text #6

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.5085. Min Act: -0.0001

Data Index: 85984 (C4 (Web Text))

Max Activating Token Index: 457

Text #7

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.4371. Min Act: -0.0001

Data Index: 735016 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.4397. Min Act: -0.0000

Data Index: 464546 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.5153. Min Act: -0.0000

Data Index: 678949 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.3485. Min Act: -0.0001

Data Index: 350022 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.4863. Min Act: -0.0000

Data Index: 455523 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.4376. Min Act: -0.0001

Data Index: 711987 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.5089. Min Act: -0.0000

Data Index: 666363 (C4 (Web Text))

Max Activating Token Index: 483

Text #14

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.3361. Min Act: -0.0001

Data Index: 388950 (C4 (Web Text))

Max Activating Token Index: 620

Text #15

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.5595. Min Act: -0.0001

Data Index: 1226962 (C4 (Web Text))

Max Activating Token Index: 352

Text #16

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.3805. Min Act: -0.0001

Data Index: 165021 (C4 (Web Text))

Max Activating Token Index: 858

Text #17

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.3434. Min Act: -0.0000

Data Index: 85049 (C4 (Web Text))

Max Activating Token Index: 607

Text #18

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.5635. Min Act: -0.0001

Data Index: 933747 (C4 (Web Text))

Max Activating Token Index: 525

Text #19

Max Range: 1.9010. Min Range: -1.9010

Max Act: 1.3909. Min Act: -0.0001

Data Index: 589052 (C4 (Web Text))

Max Activating Token Index: 864