Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 813 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.5253. Min Act: -0.1700

Data Index: 1137648 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.5096. Min Act: -0.1700

Data Index: 832293 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.4312. Min Act: -0.1700

Data Index: 1261149 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.4156. Min Act: -0.1700

Data Index: 1040961 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.3999. Min Act: -0.1700

Data Index: 1218548 (C4 (Web Text))

Max Activating Token Index: 486

Text #5

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.3842. Min Act: -0.1700

Data Index: 114514 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.3528. Min Act: -0.1700

Data Index: 913422 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.3685. Min Act: -0.1700

Data Index: 1217534 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.3371. Min Act: -0.1700

Data Index: 225386 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.3057. Min Act: -0.1700

Data Index: 1319972 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.2900. Min Act: -0.1700

Data Index: 296944 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.2900. Min Act: -0.1700

Data Index: 61508 (C4 (Web Text))

Max Activating Token Index: 1019

Text #12

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.2743. Min Act: -0.1700

Data Index: 819882 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.3214. Min Act: -0.1700

Data Index: 1287829 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.2743. Min Act: -0.1700

Data Index: 1115470 (C4 (Web Text))

Max Activating Token Index: 975

Text #15

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.2586. Min Act: -0.1700

Data Index: 933486 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.2429. Min Act: -0.1700

Data Index: 61940 (C4 (Web Text))

Max Activating Token Index: 53

Text #17

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.2429. Min Act: -0.1700

Data Index: 84763 (C4 (Web Text))

Max Activating Token Index: 522

Text #18

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.1957. Min Act: -0.1700

Data Index: 506218 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 3.5253. Min Range: -3.5253

Max Act: 3.1957. Min Act: -0.1700

Data Index: 366242 (C4 (Web Text))

Max Activating Token Index: 7