Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3123 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0983. Min Range: -6.0983
Max Act: 6.0983. Min Act: -0.1700
Data Index: 7302314 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.9108. Min Act: -0.1700
Data Index: 6431035 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.8483. Min Act: -0.1700
Data Index: 3782383 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.7233. Min Act: -0.1700
Data Index: 1722281 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.7233. Min Act: -0.1700
Data Index: 5573002 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.6920. Min Act: -0.1700
Data Index: 527943 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.6920. Min Act: -0.1700
Data Index: 61091 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.6608. Min Act: -0.1700
Data Index: 7756192 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.6608. Min Act: -0.1700
Data Index: 476967 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.6295. Min Act: -0.1700
Data Index: 2801222 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.5983. Min Act: -0.1700
Data Index: 2016798 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.5983. Min Act: -0.1700
Data Index: 1831314 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.5670. Min Act: -0.1700
Data Index: 8177446 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.5670. Min Act: -0.1700
Data Index: 5821916 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.5983. Min Act: -0.1700
Data Index: 3026275 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.5670. Min Act: -0.1700
Data Index: 813798 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.5983. Min Act: -0.1700
Data Index: 8805874 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.5358. Min Act: -0.1700
Data Index: 276971 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.5358. Min Act: -0.1700
Data Index: 2113806 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0983. Min Range: -6.0983
Max Act: 5.5358. Min Act: -0.1700
Data Index: 7880412 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19