Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5123 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.5561. Min Act: -0.1700
Data Index: 2365951 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.4936. Min Act: -0.1700
Data Index: 6688192 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.3999. Min Act: -0.1700
Data Index: 8512932 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.3999. Min Act: -0.1700
Data Index: 2102991 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.3061. Min Act: -0.1700
Data Index: 8293152 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.2749. Min Act: -0.1700
Data Index: 7306621 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.2749. Min Act: -0.1700
Data Index: 5090427 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.2749. Min Act: -0.1700
Data Index: 2391688 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.2749. Min Act: -0.1700
Data Index: 4983338 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.2436. Min Act: -0.1700
Data Index: 3005680 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.1499. Min Act: -0.1700
Data Index: 3580190 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.1499. Min Act: -0.1700
Data Index: 35561 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.1186. Min Act: -0.1700
Data Index: 6802595 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.1186. Min Act: -0.1700
Data Index: 7731369 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.1186. Min Act: -0.1700
Data Index: 3058190 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.1186. Min Act: -0.1700
Data Index: 8168345 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.0874. Min Act: -0.1700
Data Index: 2590866 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.0561. Min Act: -0.1700
Data Index: 2365961 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.0874. Min Act: -0.1700
Data Index: 5010888 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5561. Min Range: -7.5561
Max Act: 7.0874. Min Act: -0.1700
Data Index: 5813190 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19