Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4824. Min Range: -7.4824
Max Act: 7.4824. Min Act: -0.1700
Data Index: 4972322 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4824. Min Range: -7.4824
Max Act: 7.2324. Min Act: -0.1700
Data Index: 920218 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4824. Min Range: -7.4824
Max Act: 7.1074. Min Act: -0.1700
Data Index: 7521989 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.9824. Min Act: -0.1700
Data Index: 1267738 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.9512. Min Act: -0.1700
Data Index: 1210255 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.9512. Min Act: -0.1700
Data Index: 5927406 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.8262. Min Act: -0.1700
Data Index: 8663727 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.8262. Min Act: -0.1700
Data Index: 2923454 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.7949. Min Act: -0.1700
Data Index: 8084116 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.7949. Min Act: -0.1700
Data Index: 7934832 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.7324. Min Act: -0.1700
Data Index: 5498644 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.7324. Min Act: -0.1700
Data Index: 4784284 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.7324. Min Act: -0.1700
Data Index: 2923448 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.7324. Min Act: -0.1700
Data Index: 1971382 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.7012. Min Act: -0.1700
Data Index: 250746 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.6699. Min Act: -0.1700
Data Index: 1106528 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.6699. Min Act: -0.1700
Data Index: 720336 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.6699. Min Act: -0.1700
Data Index: 3877098 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.6074. Min Act: -0.1700
Data Index: 4816605 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4824. Min Range: -7.4824
Max Act: 6.6074. Min Act: -0.1700
Data Index: 4609497 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19