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

Dataset: Open Web Text

Neuron 2062 in Layer 1

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: 3.4191. Min Range: -3.4191

Max Act: 3.4191. Min Act: -0.1700

Data Index: 4358396 (Open Web Text)

Max Activating Token Index: 220

Text #1

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.4154. Min Act: -0.1700

Data Index: 2510440 (Open Web Text)

Max Activating Token Index: 816

Text #2

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3700. Min Act: -0.1700

Data Index: 4026056 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3393. Min Act: -0.1700

Data Index: 4261908 (Open Web Text)

Max Activating Token Index: 113

Text #4

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3433. Min Act: -0.1700

Data Index: 928550 (Open Web Text)

Max Activating Token Index: 136

Text #5

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3177. Min Act: -0.1700

Data Index: 7356392 (Open Web Text)

Max Activating Token Index: 217

Text #6

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3053. Min Act: -0.1700

Data Index: 1921094 (Open Web Text)

Max Activating Token Index: 69

Text #7

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3050. Min Act: -0.1700

Data Index: 2815055 (Open Web Text)

Max Activating Token Index: 246

Text #8

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3073. Min Act: -0.1700

Data Index: 1265566 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3045. Min Act: -0.1700

Data Index: 1297954 (Open Web Text)

Max Activating Token Index: 262

Text #10

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3042. Min Act: -0.1700

Data Index: 5239864 (Open Web Text)

Max Activating Token Index: 1022

Text #11

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3028. Min Act: -0.1700

Data Index: 7166145 (Open Web Text)

Max Activating Token Index: 563

Text #12

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2825. Min Act: -0.1700

Data Index: 915674 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2953. Min Act: -0.1700

Data Index: 6476026 (Open Web Text)

Max Activating Token Index: 407

Text #14

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2884. Min Act: -0.1700

Data Index: 3296188 (Open Web Text)

Max Activating Token Index: 475

Text #15

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2958. Min Act: -0.1700

Data Index: 5262612 (Open Web Text)

Max Activating Token Index: 1022

Text #16

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2935. Min Act: -0.1700

Data Index: 2919981 (Open Web Text)

Max Activating Token Index: 475

Text #17

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2957. Min Act: -0.1700

Data Index: 880940 (Open Web Text)

Max Activating Token Index: 169

Text #18

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.2880. Min Act: -0.1700

Data Index: 1180842 (Open Web Text)

Max Activating Token Index: 443

Text #19

Max Range: 3.4191. Min Range: -3.4191

Max Act: 3.3028. Min Act: -0.1700

Data Index: 1684434 (Open Web Text)

Max Activating Token Index: 985