Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4820 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.6883. Min Act: -0.1700
Data Index: 1633557 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.5633. Min Act: -0.1700
Data Index: 4885205 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.5008. Min Act: -0.1700
Data Index: 2807239 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.3758. Min Act: -0.1700
Data Index: 632338 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.3133. Min Act: -0.1700
Data Index: 7320903 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.3133. Min Act: -0.1700
Data Index: 3482309 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.2508. Min Act: -0.1700
Data Index: 1242760 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.2508. Min Act: -0.1700
Data Index: 4295287 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.2196. Min Act: -0.1700
Data Index: 5717847 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.2196. Min Act: -0.1700
Data Index: 8596243 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.2196. Min Act: -0.1700
Data Index: 955907 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.2196. Min Act: -0.1700
Data Index: 2439099 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.1883. Min Act: -0.1700
Data Index: 2930796 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.1883. Min Act: -0.1700
Data Index: 8081218 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.1883. Min Act: -0.1700
Data Index: 8645030 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.1883. Min Act: -0.1700
Data Index: 5690774 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.1883. Min Act: -0.1700
Data Index: 7350380 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.1571. Min Act: -0.1700
Data Index: 2899739 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.1571. Min Act: -0.1700
Data Index: 67784 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6883. Min Range: -5.6883
Max Act: 5.1571. Min Act: -0.1700
Data Index: 7276524 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #19