Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 1391 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.5965. Min Act: -0.1700

Data Index: 1503418 (Python Code)

Max Activating Token Index: 13

Text #1

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4922. Min Act: -0.1700

Data Index: 1410482 (Python Code)

Max Activating Token Index: 10

Text #2

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4992. Min Act: -0.1700

Data Index: 1569742 (Python Code)

Max Activating Token Index: 7

Text #3

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4221. Min Act: -0.1700

Data Index: 1615785 (Python Code)

Max Activating Token Index: 36

Text #4

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.3759. Min Act: -0.1700

Data Index: 1624042 (Python Code)

Max Activating Token Index: 59

Text #5

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.4099. Min Act: -0.1700

Data Index: 1362305 (Python Code)

Max Activating Token Index: 9

Text #6

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.3406. Min Act: -0.1700

Data Index: 1585250 (Python Code)

Max Activating Token Index: 85

Text #7

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.3682. Min Act: -0.1700

Data Index: 1605950 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.3569. Min Act: -0.1700

Data Index: 1631446 (Python Code)

Max Activating Token Index: 380

Text #9

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.3593. Min Act: -0.1700

Data Index: 1438429 (Python Code)

Max Activating Token Index: 763

Text #10

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.3169. Min Act: -0.1700

Data Index: 1603755 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.3238. Min Act: -0.1700

Data Index: 1643494 (Python Code)

Max Activating Token Index: 9

Text #12

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.2974. Min Act: -0.1700

Data Index: 1642333 (Python Code)

Max Activating Token Index: 112

Text #13

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.2610. Min Act: -0.1700

Data Index: 1507393 (Python Code)

Max Activating Token Index: 216

Text #14

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.2866. Min Act: -0.1700

Data Index: 1557175 (Python Code)

Max Activating Token Index: 9

Text #15

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.2697. Min Act: -0.1700

Data Index: 1528821 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.2931. Min Act: -0.1700

Data Index: 1446544 (Python Code)

Max Activating Token Index: 16

Text #17

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.2937. Min Act: -0.1700

Data Index: 1548058 (Python Code)

Max Activating Token Index: 12

Text #18

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.3064. Min Act: -0.1700

Data Index: 1448230 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 4.5965. Min Range: -4.5965

Max Act: 4.3364. Min Act: -0.1700

Data Index: 1555452 (Python Code)

Max Activating Token Index: 929