Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1324 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.4284. Min Act: -0.1700

Data Index: 902363 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.4597. Min Act: -0.1700

Data Index: 1197311 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.4597. Min Act: -0.1700

Data Index: 1156544 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.3342. Min Act: -0.1700

Data Index: 1354557 (C4 (Web Text))

Max Activating Token Index: 225

Text #4

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.2714. Min Act: -0.1700

Data Index: 423337 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.2871. Min Act: -0.1700

Data Index: 401473 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.2400. Min Act: -0.1700

Data Index: 1061021 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.2243. Min Act: -0.1700

Data Index: 279630 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.1928. Min Act: -0.1700

Data Index: 1059547 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.1771. Min Act: -0.1700

Data Index: 374470 (C4 (Web Text))

Max Activating Token Index: 455

Text #10

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.1456. Min Act: -0.1700

Data Index: 1208956 (C4 (Web Text))

Max Activating Token Index: 779

Text #11

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.1613. Min Act: -0.1700

Data Index: 1353263 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.1928. Min Act: -0.1700

Data Index: 486058 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.1456. Min Act: -0.1700

Data Index: 1340057 (C4 (Web Text))

Max Activating Token Index: 898

Text #14

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.1771. Min Act: -0.1700

Data Index: 119511 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.1298. Min Act: -0.1700

Data Index: 879097 (C4 (Web Text))

Max Activating Token Index: 37

Text #16

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.1141. Min Act: -0.1700

Data Index: 106198 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.1298. Min Act: -0.1700

Data Index: 440449 (C4 (Web Text))

Max Activating Token Index: 793

Text #18

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.0983. Min Act: -0.1700

Data Index: 266559 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 3.4597. Min Range: -3.4597

Max Act: 3.0983. Min Act: -0.1700

Data Index: 491775 (C4 (Web Text))

Max Activating Token Index: 737