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

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

Neuron 1379 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3916. Min Act: -0.0001

Data Index: 1522519 (Python Code)

Max Activating Token Index: 247

Text #1

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3858. Min Act: -0.0001

Data Index: 1493655 (Python Code)

Max Activating Token Index: 111

Text #2

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3596. Min Act: -0.0001

Data Index: 1627824 (Python Code)

Max Activating Token Index: 985

Text #3

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1589068 (Python Code)

Max Activating Token Index: 759

Text #4

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3598. Min Act: -0.0000

Data Index: 1596647 (Python Code)

Max Activating Token Index: 614

Text #5

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3492. Min Act: -0.0001

Data Index: 1439467 (Python Code)

Max Activating Token Index: 102

Text #6

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3484. Min Act: -0.0000

Data Index: 1517993 (Python Code)

Max Activating Token Index: 549

Text #7

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3364. Min Act: -0.0000

Data Index: 1536134 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3315. Min Act: -0.0001

Data Index: 1478022 (Python Code)

Max Activating Token Index: 790

Text #9

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3466. Min Act: -0.0001

Data Index: 1439098 (Python Code)

Max Activating Token Index: 238

Text #10

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3336. Min Act: -0.0001

Data Index: 1365466 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3404. Min Act: -0.0001

Data Index: 1476376 (Python Code)

Max Activating Token Index: 789

Text #12

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3234. Min Act: -0.0001

Data Index: 1472390 (Python Code)

Max Activating Token Index: 768

Text #13

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3206. Min Act: -0.0001

Data Index: 1443526 (Python Code)

Max Activating Token Index: 924

Text #14

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3308. Min Act: -0.0001

Data Index: 1374643 (Python Code)

Max Activating Token Index: 326

Text #15

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3194. Min Act: -0.0000

Data Index: 1424809 (Python Code)

Max Activating Token Index: 330

Text #16

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3273. Min Act: -0.0001

Data Index: 1366768 (Python Code)

Max Activating Token Index: 245

Text #17

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3147. Min Act: -0.0001

Data Index: 1652574 (Python Code)

Max Activating Token Index: 560

Text #18

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3257. Min Act: -0.0001

Data Index: 1415120 (Python Code)

Max Activating Token Index: 104

Text #19

Max Range: 0.3916. Min Range: -0.3916

Max Act: 0.3261. Min Act: -0.0001

Data Index: 1538731 (Python Code)

Max Activating Token Index: 372