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

Dataset: Open Web Text

Neuron 2723 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: 3.4991. Min Range: -3.4991

Max Act: 3.4991. Min Act: -0.1700

Data Index: 4147116 (Open Web Text)

Max Activating Token Index: 272

Text #1

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.4893. Min Act: -0.1700

Data Index: 6743989 (Open Web Text)

Max Activating Token Index: 728

Text #2

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.4186. Min Act: -0.1700

Data Index: 3660290 (Open Web Text)

Max Activating Token Index: 83

Text #3

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.4091. Min Act: -0.1700

Data Index: 6727544 (Open Web Text)

Max Activating Token Index: 58

Text #4

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.4188. Min Act: -0.1700

Data Index: 2324974 (Open Web Text)

Max Activating Token Index: 708

Text #5

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3911. Min Act: -0.1700

Data Index: 3460828 (Open Web Text)

Max Activating Token Index: 960

Text #6

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3986. Min Act: -0.1700

Data Index: 5100648 (Open Web Text)

Max Activating Token Index: 407

Text #7

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.4033. Min Act: -0.1700

Data Index: 8588970 (Open Web Text)

Max Activating Token Index: 493

Text #8

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3854. Min Act: -0.1700

Data Index: 3170383 (Open Web Text)

Max Activating Token Index: 581

Text #9

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3800. Min Act: -0.1700

Data Index: 7188531 (Open Web Text)

Max Activating Token Index: 349

Text #10

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3789. Min Act: -0.1700

Data Index: 8076817 (Open Web Text)

Max Activating Token Index: 274

Text #11

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3842. Min Act: -0.1700

Data Index: 68061 (Open Web Text)

Max Activating Token Index: 404

Text #12

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3707. Min Act: -0.1700

Data Index: 2402504 (Open Web Text)

Max Activating Token Index: 127

Text #13

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3773. Min Act: -0.1700

Data Index: 7466030 (Open Web Text)

Max Activating Token Index: 53

Text #14

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3698. Min Act: -0.1700

Data Index: 1183312 (Open Web Text)

Max Activating Token Index: 47

Text #15

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3553. Min Act: -0.1700

Data Index: 664578 (Open Web Text)

Max Activating Token Index: 37

Text #16

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3586. Min Act: -0.1700

Data Index: 3670286 (Open Web Text)

Max Activating Token Index: 129

Text #17

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3592. Min Act: -0.1700

Data Index: 144986 (Open Web Text)

Max Activating Token Index: 47

Text #18

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3460. Min Act: -0.1700

Data Index: 7324678 (Open Web Text)

Max Activating Token Index: 387

Text #19

Max Range: 3.4991. Min Range: -3.4991

Max Act: 3.3303. Min Act: -0.1700

Data Index: 5732819 (Open Web Text)

Max Activating Token Index: 715