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

Dataset: Open Web Text

Neuron 1920 in Layer 3

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: 4.3943. Min Range: -4.3943

Max Act: 4.3943. Min Act: -0.1700

Data Index: 339840 (Open Web Text)

Max Activating Token Index: 194

Text #1

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3541. Min Act: -0.1700

Data Index: 4403735 (Open Web Text)

Max Activating Token Index: 947

Text #2

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3918. Min Act: -0.1700

Data Index: 6662225 (Open Web Text)

Max Activating Token Index: 491

Text #3

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3593. Min Act: -0.1700

Data Index: 6914193 (Open Web Text)

Max Activating Token Index: 656

Text #4

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3711. Min Act: -0.1700

Data Index: 2474529 (Open Web Text)

Max Activating Token Index: 369

Text #5

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3478. Min Act: -0.1700

Data Index: 5847725 (Open Web Text)

Max Activating Token Index: 993

Text #6

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3310. Min Act: -0.1700

Data Index: 6307245 (Open Web Text)

Max Activating Token Index: 141

Text #7

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3065. Min Act: -0.1700

Data Index: 4889303 (Open Web Text)

Max Activating Token Index: 998

Text #8

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3363. Min Act: -0.1700

Data Index: 5222828 (Open Web Text)

Max Activating Token Index: 49

Text #9

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3268. Min Act: -0.1700

Data Index: 6254808 (Open Web Text)

Max Activating Token Index: 489

Text #10

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3195. Min Act: -0.1700

Data Index: 32898 (Open Web Text)

Max Activating Token Index: 792

Text #11

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.2979. Min Act: -0.1700

Data Index: 5605004 (Open Web Text)

Max Activating Token Index: 531

Text #12

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3319. Min Act: -0.1700

Data Index: 1648251 (Open Web Text)

Max Activating Token Index: 185

Text #13

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3168. Min Act: -0.1700

Data Index: 3064278 (Open Web Text)

Max Activating Token Index: 632

Text #14

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3205. Min Act: -0.1700

Data Index: 4783921 (Open Web Text)

Max Activating Token Index: 57

Text #15

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3196. Min Act: -0.1700

Data Index: 4700898 (Open Web Text)

Max Activating Token Index: 758

Text #16

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.2608. Min Act: -0.1700

Data Index: 4922711 (Open Web Text)

Max Activating Token Index: 1022

Text #17

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.2919. Min Act: -0.1700

Data Index: 3522436 (Open Web Text)

Max Activating Token Index: 823

Text #18

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.3130. Min Act: -0.1700

Data Index: 423533 (Open Web Text)

Max Activating Token Index: 945

Text #19

Max Range: 4.3943. Min Range: -4.3943

Max Act: 4.2495. Min Act: -0.1700

Data Index: 4026662 (Open Web Text)

Max Activating Token Index: 953