Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2633. Min Range: -5.2633
Max Act: 5.2633. Min Act: -0.1700
Data Index: 382654 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.8571. Min Act: -0.1700
Data Index: 7136968 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.7946. Min Act: -0.1700
Data Index: 2689888 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.7633. Min Act: -0.1700
Data Index: 1582468 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.7008. Min Act: -0.1700
Data Index: 8806721 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.7008. Min Act: -0.1700
Data Index: 2276733 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.7321. Min Act: -0.1700
Data Index: 643765 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.6696. Min Act: -0.1700
Data Index: 5472189 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.6696. Min Act: -0.1700
Data Index: 6833786 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.6383. Min Act: -0.1700
Data Index: 5544331 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.6696. Min Act: -0.1700
Data Index: 4712118 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.6071. Min Act: -0.1700
Data Index: 4252952 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.6383. Min Act: -0.1700
Data Index: 6560593 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.6383. Min Act: -0.1700
Data Index: 761292 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.6071. Min Act: -0.1700
Data Index: 3846902 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.6071. Min Act: -0.1700
Data Index: 8820675 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.6071. Min Act: -0.1700
Data Index: 7382268 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.5758. Min Act: -0.1700
Data Index: 687043 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.5758. Min Act: -0.1700
Data Index: 938731 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2633. Min Range: -5.2633
Max Act: 4.5446. Min Act: -0.1700
Data Index: 6641927 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19