Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1994 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7756. Min Act: -0.1369

Data Index: 2262600 (Open Web Text)

Max Activating Token Index: 1005

Text #1

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7671. Min Act: -0.1369

Data Index: 4091170 (Open Web Text)

Max Activating Token Index: 1020

Text #2

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7573. Min Act: -0.1369

Data Index: 4999527 (Open Web Text)

Max Activating Token Index: 1015

Text #3

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7586. Min Act: -0.1369

Data Index: 2684475 (Open Web Text)

Max Activating Token Index: 992

Text #4

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7568. Min Act: -0.1369

Data Index: 441422 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7551. Min Act: -0.1369

Data Index: 189095 (Open Web Text)

Max Activating Token Index: 1014

Text #6

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7582. Min Act: -0.1369

Data Index: 8415029 (Open Web Text)

Max Activating Token Index: 1014

Text #7

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7538. Min Act: -0.1692

Data Index: 4598504 (Open Web Text)

Max Activating Token Index: 1013

Text #8

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7520. Min Act: -0.1369

Data Index: 6146132 (Open Web Text)

Max Activating Token Index: 1020

Text #9

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7510. Min Act: -0.1369

Data Index: 3772557 (Open Web Text)

Max Activating Token Index: 997

Text #10

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7460. Min Act: -0.1369

Data Index: 1027446 (Open Web Text)

Max Activating Token Index: 998

Text #11

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7516. Min Act: -0.1369

Data Index: 162848 (Open Web Text)

Max Activating Token Index: 971

Text #12

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7444. Min Act: -0.1369

Data Index: 3008071 (Open Web Text)

Max Activating Token Index: 1009

Text #13

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7474. Min Act: -0.1369

Data Index: 6110126 (Open Web Text)

Max Activating Token Index: 1005

Text #14

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7403. Min Act: -0.1369

Data Index: 3666287 (Open Web Text)

Max Activating Token Index: 1016

Text #15

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7371. Min Act: -0.1369

Data Index: 306884 (Open Web Text)

Max Activating Token Index: 1006

Text #16

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7452. Min Act: -0.1369

Data Index: 2488774 (Open Web Text)

Max Activating Token Index: 1018

Text #17

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7422. Min Act: -0.1369

Data Index: 5339028 (Open Web Text)

Max Activating Token Index: 1013

Text #18

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7450. Min Act: -0.1369

Data Index: 5857737 (Open Web Text)

Max Activating Token Index: 1014

Text #19

Max Range: 1.7756. Min Range: -1.7756

Max Act: 1.7435. Min Act: -0.1399

Data Index: 4091167 (Open Web Text)

Max Activating Token Index: 989