Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6453. Min Range: -3.6453
Max Act: 3.6453. Min Act: -0.1700
Data Index: 6628834 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6453. Min Range: -3.6453
Max Act: 3.2692. Min Act: -0.1700
Data Index: 3792918 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6453. Min Range: -3.6453
Max Act: 3.1119. Min Act: -0.1700
Data Index: 4442894 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6453. Min Range: -3.6453
Max Act: 3.1119. Min Act: -0.1700
Data Index: 3599407 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6453. Min Range: -3.6453
Max Act: 3.0646. Min Act: -0.1700
Data Index: 3401133 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6453. Min Range: -3.6453
Max Act: 3.0489. Min Act: -0.1700
Data Index: 6164173 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6453. Min Range: -3.6453
Max Act: 3.0489. Min Act: -0.1700
Data Index: 5129618 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6453. Min Range: -3.6453
Max Act: 3.0331. Min Act: -0.1700
Data Index: 8724451 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6453. Min Range: -3.6453
Max Act: 3.0331. Min Act: -0.1700
Data Index: 8520181 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6453. Min Range: -3.6453
Max Act: 3.0015. Min Act: -0.1700
Data Index: 2756339 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6453. Min Range: -3.6453
Max Act: 3.0015. Min Act: -0.1700
Data Index: 2473289 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6453. Min Range: -3.6453
Max Act: 2.9857. Min Act: -0.1700
Data Index: 6794385 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6453. Min Range: -3.6453
Max Act: 3.0015. Min Act: -0.1700
Data Index: 5943255 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6453. Min Range: -3.6453
Max Act: 2.9857. Min Act: -0.1700
Data Index: 352853 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6453. Min Range: -3.6453
Max Act: 2.9857. Min Act: -0.1700
Data Index: 2313481 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6453. Min Range: -3.6453
Max Act: 2.9699. Min Act: -0.1700
Data Index: 6361377 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6453. Min Range: -3.6453
Max Act: 2.9540. Min Act: -0.1700
Data Index: 413899 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6453. Min Range: -3.6453
Max Act: 2.9699. Min Act: -0.1700
Data Index: 6961774 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6453. Min Range: -3.6453
Max Act: 2.9540. Min Act: -0.1700
Data Index: 5721268 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6453. Min Range: -3.6453
Max Act: 2.9382. Min Act: -0.1700
Data Index: 297679 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19