Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2453 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1221. Min Range: -6.1221
Max Act: 6.1221. Min Act: -0.1700
Data Index: 1960354 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.9346. Min Act: -0.1700
Data Index: 877022 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.8721. Min Act: -0.1700
Data Index: 3608299 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.8096. Min Act: -0.1700
Data Index: 3915266 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.6533. Min Act: -0.1700
Data Index: 2277976 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.6221. Min Act: -0.1700
Data Index: 2731449 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.6221. Min Act: -0.1700
Data Index: 645650 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.5908. Min Act: -0.1700
Data Index: 81311 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.6221. Min Act: -0.1700
Data Index: 6133288 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.6221. Min Act: -0.1700
Data Index: 8215071 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.5908. Min Act: -0.1700
Data Index: 5161771 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.5908. Min Act: -0.1700
Data Index: 1747188 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.5596. Min Act: -0.1700
Data Index: 7275958 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.5596. Min Act: -0.1700
Data Index: 8149586 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.5283. Min Act: -0.1700
Data Index: 1751209 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.5283. Min Act: -0.1700
Data Index: 6231354 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.5283. Min Act: -0.1700
Data Index: 8169456 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.5283. Min Act: -0.1700
Data Index: 7836355 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.4971. Min Act: -0.1700
Data Index: 3771359 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1221. Min Range: -6.1221
Max Act: 5.4971. Min Act: -0.1700
Data Index: 2016655 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19