Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5222 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1050. Min Range: -7.1050
Max Act: 7.1050. Min Act: -0.1700
Data Index: 8164503 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.7925. Min Act: -0.1700
Data Index: 7829109 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.7925. Min Act: -0.1700
Data Index: 7829107 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.7925. Min Act: -0.1700
Data Index: 1318331 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.7613. Min Act: -0.1700
Data Index: 3811370 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.7613. Min Act: -0.1700
Data Index: 567389 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.7300. Min Act: -0.1700
Data Index: 7215162 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.6988. Min Act: -0.1700
Data Index: 736759 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.6988. Min Act: -0.1700
Data Index: 4934319 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.6675. Min Act: -0.1700
Data Index: 7452338 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.6363. Min Act: -0.1700
Data Index: 5311539 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.6050. Min Act: -0.1700
Data Index: 5376698 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.6050. Min Act: -0.1700
Data Index: 8180873 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.6050. Min Act: -0.1700
Data Index: 1747 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.6050. Min Act: -0.1700
Data Index: 4962238 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.6050. Min Act: -0.1700
Data Index: 997671 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.5738. Min Act: -0.1700
Data Index: 2849836 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.6050. Min Act: -0.1700
Data Index: 3161795 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.5425. Min Act: -0.1700
Data Index: 7716856 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1050. Min Range: -7.1050
Max Act: 6.5738. Min Act: -0.1700
Data Index: 7764127 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19