Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.6571. Min Act: -0.1700
Data Index: 18185 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.5321. Min Act: -0.1700
Data Index: 5411726 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.5634. Min Act: -0.1700
Data Index: 7343879 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.5321. Min Act: -0.1700
Data Index: 5792950 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.4696. Min Act: -0.1700
Data Index: 3910687 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.4696. Min Act: -0.1700
Data Index: 3665764 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.4384. Min Act: -0.1700
Data Index: 5389931 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.4384. Min Act: -0.1700
Data Index: 5389935 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.3759. Min Act: -0.1700
Data Index: 5389928 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.4071. Min Act: -0.1700
Data Index: 3221672 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.3134. Min Act: -0.1700
Data Index: 5389930 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.3446. Min Act: -0.1700
Data Index: 5782682 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.3446. Min Act: -0.1700
Data Index: 5389929 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.3134. Min Act: -0.1700
Data Index: 7209951 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.3134. Min Act: -0.1700
Data Index: 5389934 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.2509. Min Act: -0.1700
Data Index: 7205616 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.2196. Min Act: -0.1700
Data Index: 3114088 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.2821. Min Act: -0.1700
Data Index: 4746637 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.2196. Min Act: -0.1700
Data Index: 8346693 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6571. Min Range: -7.6571
Max Act: 7.1884. Min Act: -0.1700
Data Index: 7799750 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19