Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2477 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.9411. Min Act: -0.1700
Data Index: 5115912 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.8474. Min Act: -0.1700
Data Index: 2971042 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.7536. Min Act: -0.1700
Data Index: 4480445 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.6911. Min Act: -0.1700
Data Index: 615146 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.6599. Min Act: -0.1700
Data Index: 8559856 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.6286. Min Act: -0.1700
Data Index: 4838798 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.5974. Min Act: -0.1700
Data Index: 2951713 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.5974. Min Act: -0.1700
Data Index: 5439277 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.5661. Min Act: -0.1700
Data Index: 7802001 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.5036. Min Act: -0.1700
Data Index: 3494135 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.4724. Min Act: -0.1700
Data Index: 4652380 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.4724. Min Act: -0.1700
Data Index: 881280 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.4724. Min Act: -0.1700
Data Index: 6211469 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.4724. Min Act: -0.1700
Data Index: 4349303 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.4724. Min Act: -0.1700
Data Index: 5327519 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.4724. Min Act: -0.1700
Data Index: 517451 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.4411. Min Act: -0.1700
Data Index: 8413952 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.4099. Min Act: -0.1700
Data Index: 4161292 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.4099. Min Act: -0.1700
Data Index: 4679891 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9411. Min Range: -5.9411
Max Act: 5.4099. Min Act: -0.1700
Data Index: 6627878 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #19