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

Dataset: Open Web Text

Neuron 1435 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: 4.7479. Min Range: -4.7479

Max Act: 4.7479. Min Act: -0.1700

Data Index: 694918 (Open Web Text)

Max Activating Token Index: 1009

Text #1

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.6704. Min Act: -0.1700

Data Index: 8023954 (Open Web Text)

Max Activating Token Index: 407

Text #2

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.5957. Min Act: -0.1700

Data Index: 3610776 (Open Web Text)

Max Activating Token Index: 140

Text #3

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.5548. Min Act: -0.1700

Data Index: 1381977 (Open Web Text)

Max Activating Token Index: 235

Text #4

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.5040. Min Act: -0.1700

Data Index: 6982804 (Open Web Text)

Max Activating Token Index: 156

Text #5

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.4796. Min Act: -0.1700

Data Index: 3801080 (Open Web Text)

Max Activating Token Index: 819

Text #6

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.4550. Min Act: -0.1700

Data Index: 6505745 (Open Web Text)

Max Activating Token Index: 484

Text #7

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.4567. Min Act: -0.1700

Data Index: 1783791 (Open Web Text)

Max Activating Token Index: 746

Text #8

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.4476. Min Act: -0.1700

Data Index: 3672679 (Open Web Text)

Max Activating Token Index: 11

Text #9

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.4259. Min Act: -0.1700

Data Index: 1615057 (Open Web Text)

Max Activating Token Index: 700

Text #10

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.4371. Min Act: -0.1700

Data Index: 1772135 (Open Web Text)

Max Activating Token Index: 141

Text #11

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.4267. Min Act: -0.1700

Data Index: 3077695 (Open Web Text)

Max Activating Token Index: 131

Text #12

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.4119. Min Act: -0.1700

Data Index: 7133829 (Open Web Text)

Max Activating Token Index: 158

Text #13

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.3869. Min Act: -0.1700

Data Index: 418828 (Open Web Text)

Max Activating Token Index: 3

Text #14

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.3942. Min Act: -0.1700

Data Index: 5631897 (Open Web Text)

Max Activating Token Index: 51

Text #15

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.3948. Min Act: -0.1700

Data Index: 6222505 (Open Web Text)

Max Activating Token Index: 494

Text #16

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.4161. Min Act: -0.1700

Data Index: 1240598 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.3869. Min Act: -0.1700

Data Index: 5830605 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.3787. Min Act: -0.1700

Data Index: 2851270 (Open Web Text)

Max Activating Token Index: 5

Text #19

Max Range: 4.7479. Min Range: -4.7479

Max Act: 4.3952. Min Act: -0.1700

Data Index: 5697128 (Open Web Text)

Max Activating Token Index: 357