Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.7277. Min Act: -0.1700
Data Index: 1329492 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.5089. Min Act: -0.1700
Data Index: 406099 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.4152. Min Act: -0.1700
Data Index: 6811515 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.4152. Min Act: -0.1700
Data Index: 6099590 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.4152. Min Act: -0.1700
Data Index: 5903567 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.4152. Min Act: -0.1700
Data Index: 1639930 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.3839. Min Act: -0.1700
Data Index: 3690704 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.3839. Min Act: -0.1700
Data Index: 4570195 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.3527. Min Act: -0.1700
Data Index: 6996841 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.3839. Min Act: -0.1700
Data Index: 2890021 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.3214. Min Act: -0.1700
Data Index: 3381619 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.3214. Min Act: -0.1700
Data Index: 5048782 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.2902. Min Act: -0.1700
Data Index: 533419 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.3214. Min Act: -0.1700
Data Index: 1160160 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.2902. Min Act: -0.1700
Data Index: 3601175 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.2589. Min Act: -0.1700
Data Index: 271720 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.2902. Min Act: -0.1700
Data Index: 2991784 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.2589. Min Act: -0.1700
Data Index: 2419844 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.2902. Min Act: -0.1700
Data Index: 5874088 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7277. Min Range: -6.7277
Max Act: 6.2902. Min Act: -0.1700
Data Index: 6535033 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #19