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

Dataset: Open Web Text

Neuron 180 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: 1.1959. Min Range: -1.1959

Max Act: 1.1927. Min Act: -0.0669

Data Index: 6278248 (Open Web Text)

Max Activating Token Index: 1009

Text #1

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1959. Min Act: -0.0992

Data Index: 7044651 (Open Web Text)

Max Activating Token Index: 995

Text #2

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1944. Min Act: -0.0669

Data Index: 1237450 (Open Web Text)

Max Activating Token Index: 1013

Text #3

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1854. Min Act: -0.0831

Data Index: 1451563 (Open Web Text)

Max Activating Token Index: 1016

Text #4

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1797. Min Act: -0.0669

Data Index: 1531165 (Open Web Text)

Max Activating Token Index: 1022

Text #5

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1701. Min Act: -0.0669

Data Index: 3015996 (Open Web Text)

Max Activating Token Index: 1017

Text #6

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1678. Min Act: -0.0928

Data Index: 6114831 (Open Web Text)

Max Activating Token Index: 1004

Text #7

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1642. Min Act: -0.0669

Data Index: 8259990 (Open Web Text)

Max Activating Token Index: 1013

Text #8

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1528. Min Act: -0.0846

Data Index: 3375339 (Open Web Text)

Max Activating Token Index: 1022

Text #9

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1645. Min Act: -0.0669

Data Index: 7574606 (Open Web Text)

Max Activating Token Index: 1021

Text #10

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1569. Min Act: -0.0990

Data Index: 7676662 (Open Web Text)

Max Activating Token Index: 993

Text #11

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1686. Min Act: -0.0705

Data Index: 5930200 (Open Web Text)

Max Activating Token Index: 1015

Text #12

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1534. Min Act: -0.0713

Data Index: 3862448 (Open Web Text)

Max Activating Token Index: 1011

Text #13

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1445. Min Act: -0.0842

Data Index: 3781546 (Open Web Text)

Max Activating Token Index: 1020

Text #14

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1575. Min Act: -0.0669

Data Index: 1460428 (Open Web Text)

Max Activating Token Index: 1021

Text #15

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1440. Min Act: -0.1117

Data Index: 7085648 (Open Web Text)

Max Activating Token Index: 1013

Text #16

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1477. Min Act: -0.0669

Data Index: 2245919 (Open Web Text)

Max Activating Token Index: 1020

Text #17

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1461. Min Act: -0.0669

Data Index: 6712235 (Open Web Text)

Max Activating Token Index: 1020

Text #18

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1538. Min Act: -0.0669

Data Index: 3612337 (Open Web Text)

Max Activating Token Index: 1019

Text #19

Max Range: 1.1959. Min Range: -1.1959

Max Act: 1.1440. Min Act: -0.0669

Data Index: 4592545 (Open Web Text)

Max Activating Token Index: 1019