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

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

Neuron 5210 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1578320 (Python Code)

Max Activating Token Index: 978

Text #1

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1334206 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6039. Min Act: -0.0000

Data Index: 445277 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6315. Min Act: -0.0000

Data Index: 380335 (C4 (Web Text))

Max Activating Token Index: 680

Text #4

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.6037. Min Act: -0.0000

Data Index: 966604 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5980. Min Act: -0.0000

Data Index: 237682 (C4 (Web Text))

Max Activating Token Index: 726

Text #6

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1511693 (Python Code)

Max Activating Token Index: 72

Text #7

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5514. Min Act: -0.0000

Data Index: 275186 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5553. Min Act: -0.0000

Data Index: 1574715 (Python Code)

Max Activating Token Index: 537

Text #9

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1402444 (Python Code)

Max Activating Token Index: 859

Text #10

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.4982. Min Act: -0.0000

Data Index: 728094 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5110. Min Act: -0.0000

Data Index: 832908 (C4 (Web Text))

Max Activating Token Index: 622

Text #12

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5154. Min Act: -0.0000

Data Index: 1360782 (Python Code)

Max Activating Token Index: 102

Text #13

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.4857. Min Act: -0.0000

Data Index: 114095 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5441. Min Act: -0.0000

Data Index: 1261910 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5287. Min Act: -0.0000

Data Index: 690913 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1202284 (C4 (Web Text))

Max Activating Token Index: 383

Text #17

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.4703. Min Act: -0.0000

Data Index: 1380242 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.4437. Min Act: -0.0000

Data Index: 1611070 (Python Code)

Max Activating Token Index: 833

Text #19

Max Range: 0.6950. Min Range: -0.6950

Max Act: 0.4819. Min Act: -0.0000

Data Index: 1230852 (C4 (Web Text))

Max Activating Token Index: 383