Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2503 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.9458. Min Act: -0.1700
Data Index: 490747 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.8833. Min Act: -0.1700
Data Index: 3855844 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.7583. Min Act: -0.1700
Data Index: 6465843 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.7583. Min Act: -0.1700
Data Index: 3484307 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.6958. Min Act: -0.1700
Data Index: 6038304 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.5708. Min Act: -0.1700
Data Index: 6724529 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.6333. Min Act: -0.1700
Data Index: 4434436 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.6333. Min Act: -0.1700
Data Index: 134456 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.5708. Min Act: -0.1700
Data Index: 5437224 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.5708. Min Act: -0.1700
Data Index: 1866898 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.5708. Min Act: -0.1700
Data Index: 4152635 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.5708. Min Act: -0.1700
Data Index: 7159470 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.5083. Min Act: -0.1700
Data Index: 5313088 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.5083. Min Act: -0.1700
Data Index: 8190770 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.4458. Min Act: -0.1700
Data Index: 2493476 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.4458. Min Act: -0.1700
Data Index: 5390169 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.4458. Min Act: -0.1700
Data Index: 2751693 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.4458. Min Act: -0.1700
Data Index: 32054 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.4458. Min Act: -0.1700
Data Index: 3760620 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9458. Min Range: -10.9458
Max Act: 10.4458. Min Act: -0.1700
Data Index: 2593757 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19