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

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

Neuron 1206 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: 3.4128. Min Range: -3.4128

Max Act: 3.4128. Min Act: -0.1700

Data Index: 690471 (C4 (Web Text))

Max Activating Token Index: 325

Text #1

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.4006. Min Act: -0.1700

Data Index: 677632 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.3811. Min Act: -0.1700

Data Index: 599326 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.3857. Min Act: -0.1700

Data Index: 1233136 (C4 (Web Text))

Max Activating Token Index: 385

Text #4

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.3487. Min Act: -0.1700

Data Index: 266573 (C4 (Web Text))

Max Activating Token Index: 253

Text #5

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.3482. Min Act: -0.1700

Data Index: 595675 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.3555. Min Act: -0.1700

Data Index: 916497 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.3310. Min Act: -0.1700

Data Index: 235893 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.3307. Min Act: -0.1700

Data Index: 54599 (C4 (Web Text))

Max Activating Token Index: 121

Text #9

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.2959. Min Act: -0.1700

Data Index: 78575 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.3052. Min Act: -0.1700

Data Index: 612193 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.2943. Min Act: -0.1700

Data Index: 56576 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.2946. Min Act: -0.1700

Data Index: 265223 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.3084. Min Act: -0.1700

Data Index: 1312034 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.2967. Min Act: -0.1700

Data Index: 981192 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.3051. Min Act: -0.1700

Data Index: 1127227 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.2787. Min Act: -0.1700

Data Index: 864590 (C4 (Web Text))

Max Activating Token Index: 95

Text #17

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.2687. Min Act: -0.1700

Data Index: 906522 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.2844. Min Act: -0.1700

Data Index: 1272656 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 3.4128. Min Range: -3.4128

Max Act: 3.2605. Min Act: -0.1700

Data Index: 95376 (C4 (Web Text))

Max Activating Token Index: 162