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

Dataset: Open Web Text

Neuron 1331 in Layer 2

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: 2.3009. Min Range: -2.3009

Max Act: 2.3009. Min Act: -0.1700

Data Index: 3015320 (Open Web Text)

Max Activating Token Index: 582

Text #1

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1294. Min Act: -0.1700

Data Index: 2245725 (Open Web Text)

Max Activating Token Index: 53

Text #2

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1467. Min Act: -0.1700

Data Index: 2180925 (Open Web Text)

Max Activating Token Index: 123

Text #3

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1319. Min Act: -0.1700

Data Index: 7407795 (Open Web Text)

Max Activating Token Index: 160

Text #4

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1159. Min Act: -0.1700

Data Index: 6087499 (Open Web Text)

Max Activating Token Index: 18

Text #5

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1241. Min Act: -0.1700

Data Index: 5623750 (Open Web Text)

Max Activating Token Index: 465

Text #6

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1145. Min Act: -0.1700

Data Index: 8612780 (Open Web Text)

Max Activating Token Index: 602

Text #7

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1083. Min Act: -0.1700

Data Index: 7407796 (Open Web Text)

Max Activating Token Index: 66

Text #8

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1015. Min Act: -0.1700

Data Index: 3672252 (Open Web Text)

Max Activating Token Index: 140

Text #9

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1049. Min Act: -0.1700

Data Index: 6165716 (Open Web Text)

Max Activating Token Index: 133

Text #10

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1237. Min Act: -0.1700

Data Index: 288504 (Open Web Text)

Max Activating Token Index: 820

Text #11

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1107. Min Act: -0.1700

Data Index: 7862517 (Open Web Text)

Max Activating Token Index: 588

Text #12

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1117. Min Act: -0.1700

Data Index: 1326855 (Open Web Text)

Max Activating Token Index: 539

Text #13

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.1082. Min Act: -0.1700

Data Index: 5762466 (Open Web Text)

Max Activating Token Index: 208

Text #14

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.0808. Min Act: -0.1700

Data Index: 8198657 (Open Web Text)

Max Activating Token Index: 270

Text #15

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.0869. Min Act: -0.1700

Data Index: 1840596 (Open Web Text)

Max Activating Token Index: 367

Text #16

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.0673. Min Act: -0.1700

Data Index: 3692252 (Open Web Text)

Max Activating Token Index: 194

Text #17

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.0871. Min Act: -0.1700

Data Index: 7004421 (Open Web Text)

Max Activating Token Index: 146

Text #18

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.0778. Min Act: -0.1700

Data Index: 587490 (Open Web Text)

Max Activating Token Index: 754

Text #19

Max Range: 2.3009. Min Range: -2.3009

Max Act: 2.0604. Min Act: -0.1700

Data Index: 2905257 (Open Web Text)

Max Activating Token Index: 598