Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.6314. Min Range: -8.6314
Max Act: 8.6314. Min Act: -0.1700
Data Index: 574402 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6314. Min Range: -8.6314
Max Act: 8.1939. Min Act: -0.1700
Data Index: 4487480 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6314. Min Range: -8.6314
Max Act: 8.1314. Min Act: -0.1700
Data Index: 1805926 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6314. Min Range: -8.6314
Max Act: 8.0689. Min Act: -0.1700
Data Index: 3433259 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.9439. Min Act: -0.1700
Data Index: 4821670 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.6939. Min Act: -0.1700
Data Index: 3826704 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.8189. Min Act: -0.1700
Data Index: 5007721 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.7564. Min Act: -0.1700
Data Index: 4705999 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.6939. Min Act: -0.1700
Data Index: 7969021 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.6939. Min Act: -0.1700
Data Index: 7183082 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.6314. Min Act: -0.1700
Data Index: 1464005 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.6939. Min Act: -0.1700
Data Index: 2200401 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.6314. Min Act: -0.1700
Data Index: 4485655 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.6314. Min Act: -0.1700
Data Index: 5786753 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.5689. Min Act: -0.1700
Data Index: 3420727 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.6314. Min Act: -0.1700
Data Index: 2183113 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.5689. Min Act: -0.1700
Data Index: 1146098 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.5064. Min Act: -0.1700
Data Index: 1768885 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.5064. Min Act: -0.1700
Data Index: 4327564 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6314. Min Range: -8.6314
Max Act: 7.5064. Min Act: -0.1700
Data Index: 2594581 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19