Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4419 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.5670. Min Act: -0.1700
Data Index: 7381720 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.3483. Min Act: -0.1700
Data Index: 7388318 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.3170. Min Act: -0.1700
Data Index: 7465016 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.3170. Min Act: -0.1700
Data Index: 6696836 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.3170. Min Act: -0.1700
Data Index: 4890067 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.3170. Min Act: -0.1700
Data Index: 6991269 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.2545. Min Act: -0.1700
Data Index: 2973666 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.2545. Min Act: -0.1700
Data Index: 7860364 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.1920. Min Act: -0.1700
Data Index: 8455448 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.2233. Min Act: -0.1700
Data Index: 175142 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.1608. Min Act: -0.1700
Data Index: 7844047 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.1608. Min Act: -0.1700
Data Index: 3000392 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.1295. Min Act: -0.1700
Data Index: 3712863 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.0983. Min Act: -0.1700
Data Index: 4299054 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.1608. Min Act: -0.1700
Data Index: 2886708 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.1295. Min Act: -0.1700
Data Index: 5843887 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.0983. Min Act: -0.1700
Data Index: 1800339 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.0983. Min Act: -0.1700
Data Index: 5207437 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.0983. Min Act: -0.1700
Data Index: 2293512 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5670. Min Range: -6.5670
Max Act: 6.0983. Min Act: -0.1700
Data Index: 1108096 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19