Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5843 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.9573. Min Act: -0.1700
Data Index: 2892006 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.8635. Min Act: -0.1700
Data Index: 7420491 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.7385. Min Act: -0.1700
Data Index: 8647806 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.6760. Min Act: -0.1700
Data Index: 1910509 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.6448. Min Act: -0.1700
Data Index: 7550225 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.6135. Min Act: -0.1700
Data Index: 2015721 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.6135. Min Act: -0.1700
Data Index: 3540303 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.6135. Min Act: -0.1700
Data Index: 513406 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.6135. Min Act: -0.1700
Data Index: 3777180 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.6135. Min Act: -0.1700
Data Index: 8196527 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.6135. Min Act: -0.1700
Data Index: 131498 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.5823. Min Act: -0.1700
Data Index: 434658 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.5823. Min Act: -0.1700
Data Index: 6951244 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.5823. Min Act: -0.1700
Data Index: 4065529 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.5510. Min Act: -0.1700
Data Index: 8383798 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.5510. Min Act: -0.1700
Data Index: 6566570 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.5510. Min Act: -0.1700
Data Index: 1538262 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.5510. Min Act: -0.1700
Data Index: 6223486 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.5510. Min Act: -0.1700
Data Index: 7834119 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9573. Min Range: -4.9573
Max Act: 4.5510. Min Act: -0.1700
Data Index: 2673819 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19