Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.9608. Min Act: -0.1700
Data Index: 6606439 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.9921. Min Act: -0.1700
Data Index: 7998366 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.7108. Min Act: -0.1700
Data Index: 8202254 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.6483. Min Act: -0.1700
Data Index: 5733252 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.6796. Min Act: -0.1700
Data Index: 6958361 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.6171. Min Act: -0.1700
Data Index: 358622 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.6483. Min Act: -0.1700
Data Index: 7558274 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.5546. Min Act: -0.1700
Data Index: 1795241 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.5233. Min Act: -0.1700
Data Index: 5071790 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.4921. Min Act: -0.1700
Data Index: 8308861 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.4921. Min Act: -0.1700
Data Index: 5754439 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.4296. Min Act: -0.1700
Data Index: 7693347 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.3983. Min Act: -0.1700
Data Index: 6327588 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.3983. Min Act: -0.1700
Data Index: 4676695 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.3983. Min Act: -0.1700
Data Index: 214708 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.3671. Min Act: -0.1700
Data Index: 2813882 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.3671. Min Act: -0.1700
Data Index: 7346493 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.3671. Min Act: -0.1700
Data Index: 5077442 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.3671. Min Act: -0.1700
Data Index: 6904974 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9921. Min Range: -6.9921
Max Act: 6.3671. Min Act: -0.1700
Data Index: 2075943 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19