Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4274 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.2050. Min Act: -0.1700
Data Index: 494773 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.1737. Min Act: -0.1700
Data Index: 2686698 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.1737. Min Act: -0.1700
Data Index: 5955305 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.1112. Min Act: -0.1700
Data Index: 4919150 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.0800. Min Act: -0.1700
Data Index: 168103 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.0487. Min Act: -0.1700
Data Index: 6581209 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2050. Min Range: -5.2050
Max Act: 5.0175. Min Act: -0.1700
Data Index: 4503390 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9862. Min Act: -0.1700
Data Index: 6528864 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9862. Min Act: -0.1700
Data Index: 797204 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9550. Min Act: -0.1700
Data Index: 3117103 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9550. Min Act: -0.1700
Data Index: 5714841 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9550. Min Act: -0.1699
Data Index: 3251998 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9550. Min Act: -0.1700
Data Index: 5074376 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9550. Min Act: -0.1700
Data Index: 2980998 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9237. Min Act: -0.1700
Data Index: 7392742 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.9550. Min Act: -0.1700
Data Index: 7913234 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.8925. Min Act: -0.1700
Data Index: 2634118 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.8612. Min Act: -0.1700
Data Index: 7973495 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.8925. Min Act: -0.1700
Data Index: 6461481 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2050. Min Range: -5.2050
Max Act: 4.8612. Min Act: -0.1700
Data Index: 4939505 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19