Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1443 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.7583. Min Act: -0.1700
Data Index: 8466970 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.7271. Min Act: -0.1700
Data Index: 4491609 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.7271. Min Act: -0.1700
Data Index: 7502841 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.6958. Min Act: -0.1700
Data Index: 3751200 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.6646. Min Act: -0.1700
Data Index: 6822514 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.6958. Min Act: -0.1700
Data Index: 4680028 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.6646. Min Act: -0.1700
Data Index: 3308085 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.5708. Min Act: -0.1700
Data Index: 1921328 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.6021. Min Act: -0.1700
Data Index: 3984768 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.6333. Min Act: -0.1700
Data Index: 8582960 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.5708. Min Act: -0.1700
Data Index: 6549768 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.5708. Min Act: -0.1700
Data Index: 5287658 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.5708. Min Act: -0.1700
Data Index: 3747529 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.5708. Min Act: -0.1700
Data Index: 1146091 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.5708. Min Act: -0.1700
Data Index: 4766478 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.5396. Min Act: -0.1700
Data Index: 2232377 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.5396. Min Act: -0.1700
Data Index: 5827719 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.5396. Min Act: -0.1700
Data Index: 3754988 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.4771. Min Act: -0.1700
Data Index: 6120486 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7583. Min Range: -4.7583
Max Act: 4.5083. Min Act: -0.1700
Data Index: 2376135 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19