Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5439 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.3921. Min Act: -0.1700
Data Index: 4251558 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.3608. Min Act: -0.1700
Data Index: 6258256 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.3608. Min Act: -0.1700
Data Index: 2464406 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.2983. Min Act: -0.1700
Data Index: 1737136 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.2358. Min Act: -0.1700
Data Index: 1629783 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.2671. Min Act: -0.1700
Data Index: 4155818 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.2358. Min Act: -0.1700
Data Index: 2418216 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.2046. Min Act: -0.1700
Data Index: 5289946 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.2358. Min Act: -0.1700
Data Index: 5745363 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.2358. Min Act: -0.1700
Data Index: 5855256 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.2046. Min Act: -0.1700
Data Index: 1182199 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.1733. Min Act: -0.1700
Data Index: 2740471 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.2046. Min Act: -0.1700
Data Index: 5367310 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.1420. Min Act: -0.1700
Data Index: 1588620 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.1420. Min Act: -0.1700
Data Index: 8438283 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.1733. Min Act: -0.1700
Data Index: 4193577 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.1733. Min Act: -0.1700
Data Index: 1803636 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.1420. Min Act: -0.1700
Data Index: 3386018 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.1108. Min Act: -0.1700
Data Index: 1344531 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3921. Min Range: -4.3921
Max Act: 4.1108. Min Act: -0.1700
Data Index: 5501908 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19