Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 930 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.9899. Min Act: -0.1700
Data Index: 3435039 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.9274. Min Act: -0.1700
Data Index: 8192721 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.9899. Min Act: -0.1700
Data Index: 3187273 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.9586. Min Act: -0.1700
Data Index: 1640653 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8648. Min Act: -0.1700
Data Index: 6470460 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8648. Min Act: -0.1700
Data Index: 988852 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8336. Min Act: -0.1700
Data Index: 3660513 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8336. Min Act: -0.1700
Data Index: 7900130 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8336. Min Act: -0.1700
Data Index: 5052980 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8023. Min Act: -0.1700
Data Index: 242736 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8336. Min Act: -0.1700
Data Index: 4979843 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8336. Min Act: -0.1700
Data Index: 4307581 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8023. Min Act: -0.1700
Data Index: 3833570 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8336. Min Act: -0.1700
Data Index: 2313862 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8023. Min Act: -0.1700
Data Index: 3292833 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8023. Min Act: -0.1700
Data Index: 2971060 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8023. Min Act: -0.1700
Data Index: 2855910 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8023. Min Act: -0.1700
Data Index: 2746830 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8023. Min Act: -0.1700
Data Index: 916502 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9899. Min Range: -3.9899
Max Act: 3.8023. Min Act: -0.1700
Data Index: 962326 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #19