Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3424 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.8106. Min Act: -0.1700
Data Index: 2031354 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.8106. Min Act: -0.1700
Data Index: 7535683 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.7794. Min Act: -0.1700
Data Index: 7727004 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.7169. Min Act: -0.1700
Data Index: 6653910 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.7169. Min Act: -0.1700
Data Index: 529185 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.7169. Min Act: -0.1700
Data Index: 163379 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6544. Min Act: -0.1700
Data Index: 2079866 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.6231. Min Act: -0.1700
Data Index: 3824149 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.5606. Min Act: -0.1700
Data Index: 476110 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.5606. Min Act: -0.1700
Data Index: 2686142 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.5606. Min Act: -0.1700
Data Index: 5262569 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.5294. Min Act: -0.1700
Data Index: 2460417 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.5294. Min Act: -0.1700
Data Index: 476105 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.4981. Min Act: -0.1700
Data Index: 1741836 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.4981. Min Act: -0.1700
Data Index: 3250189 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.4669. Min Act: -0.1700
Data Index: 7603032 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.4669. Min Act: -0.1700
Data Index: 3634745 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.4669. Min Act: -0.1700
Data Index: 6201467 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.4356. Min Act: -0.1700
Data Index: 5528971 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8106. Min Range: -4.8106
Max Act: 4.4669. Min Act: -0.1700
Data Index: 1098013 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19