Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2109 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.8849. Min Act: -0.1700
Data Index: 5256851 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.8224. Min Act: -0.1700
Data Index: 3814475 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.7912. Min Act: -0.1700
Data Index: 3325128 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.7287. Min Act: -0.1700
Data Index: 5318937 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.6662. Min Act: -0.1700
Data Index: 4244779 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.6349. Min Act: -0.1700
Data Index: 6406866 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5724. Min Act: -0.1700
Data Index: 8587462 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5724. Min Act: -0.1700
Data Index: 3033223 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5724. Min Act: -0.1700
Data Index: 188624 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5724. Min Act: -0.1700
Data Index: 3473486 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5724. Min Act: -0.1700
Data Index: 2557270 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5412. Min Act: -0.1700
Data Index: 5108946 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5412. Min Act: -0.1700
Data Index: 1821678 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5412. Min Act: -0.1700
Data Index: 8476021 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5412. Min Act: -0.1700
Data Index: 7779845 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5412. Min Act: -0.1700
Data Index: 4389983 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5099. Min Act: -0.1700
Data Index: 5927083 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5099. Min Act: -0.1700
Data Index: 185063 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.5412. Min Act: -0.1700
Data Index: 4779842 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8849. Min Range: -4.8849
Max Act: 4.4787. Min Act: -0.1700
Data Index: 7486545 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #19