Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2467 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4975. Min Act: -0.0001

Data Index: 1365738 (Python Code)

Max Activating Token Index: 192

Text #1

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.3660. Min Act: -0.0001

Data Index: 1370547 (Python Code)

Max Activating Token Index: 770

Text #2

Max Range: 3.4975. Min Range: -3.4975

Max Act: 3.4598. Min Act: -0.0001

Data Index: 1422700 (Python Code)

Max Activating Token Index: 594

Text #3

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.4152. Min Act: -0.0001

Data Index: 1536130 (Python Code)

Max Activating Token Index: 870

Text #4

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.4489. Min Act: -0.0000

Data Index: 1560550 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.4851. Min Act: -0.0001

Data Index: 1622189 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.4455. Min Act: -0.0001

Data Index: 1418603 (Python Code)

Max Activating Token Index: 494

Text #7

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.2326. Min Act: -0.0001

Data Index: 1560655 (Python Code)

Max Activating Token Index: 68

Text #8

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.1330. Min Act: -0.0001

Data Index: 1422325 (Python Code)

Max Activating Token Index: 856

Text #9

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.3422. Min Act: -0.0001

Data Index: 1462950 (Python Code)

Max Activating Token Index: 788

Text #10

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.1752. Min Act: -0.0001

Data Index: 1504436 (Python Code)

Max Activating Token Index: 544

Text #11

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.2717. Min Act: -0.0001

Data Index: 1632247 (Python Code)

Max Activating Token Index: 64

Text #12

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.0290. Min Act: -0.0001

Data Index: 1394452 (Python Code)

Max Activating Token Index: 622

Text #13

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.2588. Min Act: -0.0001

Data Index: 1568337 (Python Code)

Max Activating Token Index: 326

Text #14

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.2619. Min Act: -0.0001

Data Index: 1395774 (Python Code)

Max Activating Token Index: 737

Text #15

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.2430. Min Act: -0.0001

Data Index: 1643564 (Python Code)

Max Activating Token Index: 302

Text #16

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.3466. Min Act: -0.0001

Data Index: 1639009 (Python Code)

Max Activating Token Index: 611

Text #17

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.1244. Min Act: -0.0001

Data Index: 1622229 (Python Code)

Max Activating Token Index: 277

Text #18

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.2132. Min Act: -0.0001

Data Index: 1386126 (Python Code)

Max Activating Token Index: 340

Text #19

Max Range: 3.4975. Min Range: -3.4975

Max Act: 2.3070. Min Act: -0.0001

Data Index: 1485379 (Python Code)

Max Activating Token Index: 401