Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5801 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.9469. Min Act: -0.1700
Data Index: 7659844 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.9625. Min Act: -0.1700
Data Index: 3287072 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.8062. Min Act: -0.1700
Data Index: 3083911 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.7749. Min Act: -0.1700
Data Index: 5836830 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.7123. Min Act: -0.1700
Data Index: 2235353 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.6810. Min Act: -0.1700
Data Index: 1034842 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.6654. Min Act: -0.1700
Data Index: 8504568 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.5872. Min Act: -0.1700
Data Index: 4744962 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.6028. Min Act: -0.1700
Data Index: 5931860 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.5715. Min Act: -0.1700
Data Index: 7649195 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.5402. Min Act: -0.1700
Data Index: 2235363 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.5402. Min Act: -0.1700
Data Index: 3319411 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.5245. Min Act: -0.1700
Data Index: 6095268 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.5089. Min Act: -0.1700
Data Index: 8283265 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.5089. Min Act: -0.1700
Data Index: 748714 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.5089. Min Act: -0.1700
Data Index: 3291554 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.4775. Min Act: -0.1700
Data Index: 826732 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.4775. Min Act: -0.1700
Data Index: 2235354 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.4932. Min Act: -0.1700
Data Index: 3287055 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9625. Min Range: -3.9625
Max Act: 3.4775. Min Act: -0.1700
Data Index: 1248332 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19