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

Dataset: Open Web Text

Neuron 482 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: 1.3938. Min Range: -1.3938

Max Act: 1.3938. Min Act: -0.0974

Data Index: 4556719 (Open Web Text)

Max Activating Token Index: 165

Text #1

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.3389. Min Act: -0.1243

Data Index: 8075143 (Open Web Text)

Max Activating Token Index: 7

Text #2

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.3404. Min Act: -0.0910

Data Index: 2435583 (Open Web Text)

Max Activating Token Index: 716

Text #3

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.3249. Min Act: -0.1026

Data Index: 4762506 (Open Web Text)

Max Activating Token Index: 125

Text #4

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.3166. Min Act: -0.1485

Data Index: 1523774 (Open Web Text)

Max Activating Token Index: 453

Text #5

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.3178. Min Act: -0.0600

Data Index: 3118015 (Open Web Text)

Max Activating Token Index: 241

Text #6

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.3212. Min Act: -0.1522

Data Index: 1959521 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.3043. Min Act: -0.1130

Data Index: 3026337 (Open Web Text)

Max Activating Token Index: 112

Text #8

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.3066. Min Act: -0.1355

Data Index: 3161456 (Open Web Text)

Max Activating Token Index: 476

Text #9

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.3009. Min Act: -0.1572

Data Index: 4347076 (Open Web Text)

Max Activating Token Index: 228

Text #10

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2997. Min Act: -0.1263

Data Index: 5157484 (Open Web Text)

Max Activating Token Index: 436

Text #11

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.3035. Min Act: -0.1351

Data Index: 1591378 (Open Web Text)

Max Activating Token Index: 214

Text #12

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2847. Min Act: -0.1336

Data Index: 2435585 (Open Web Text)

Max Activating Token Index: 96

Text #13

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2922. Min Act: -0.1276

Data Index: 4038339 (Open Web Text)

Max Activating Token Index: 42

Text #14

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2988. Min Act: -0.1549

Data Index: 4845805 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2936. Min Act: -0.1438

Data Index: 3118013 (Open Web Text)

Max Activating Token Index: 111

Text #16

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2912. Min Act: -0.1600

Data Index: 542948 (Open Web Text)

Max Activating Token Index: 154

Text #17

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2914. Min Act: -0.1597

Data Index: 4877710 (Open Web Text)

Max Activating Token Index: 278

Text #18

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2875. Min Act: -0.1214

Data Index: 6096209 (Open Web Text)

Max Activating Token Index: 659

Text #19

Max Range: 1.3938. Min Range: -1.3938

Max Act: 1.2953. Min Act: -0.0305

Data Index: 6292690 (Open Web Text)

Max Activating Token Index: 558