Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4890 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1883. Min Range: -7.1883
Max Act: 7.1883. Min Act: -0.1700
Data Index: 4184438 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.9383. Min Act: -0.1700
Data Index: 3972959 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.8445. Min Act: -0.1700
Data Index: 5540999 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.7820. Min Act: -0.1700
Data Index: 356620 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.7820. Min Act: -0.1700
Data Index: 4354125 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.7508. Min Act: -0.1700
Data Index: 3678191 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.7195. Min Act: -0.1700
Data Index: 2152850 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.7195. Min Act: -0.1700
Data Index: 3167647 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.7195. Min Act: -0.1700
Data Index: 851923 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.6883. Min Act: -0.1700
Data Index: 3351272 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.6883. Min Act: -0.1700
Data Index: 371956 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.6570. Min Act: -0.1700
Data Index: 2196790 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.6570. Min Act: -0.1700
Data Index: 4241785 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.6570. Min Act: -0.1700
Data Index: 2152849 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.5633. Min Act: -0.1700
Data Index: 5128722 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.5633. Min Act: -0.1700
Data Index: 8750142 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.5008. Min Act: -0.1700
Data Index: 813508 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.5008. Min Act: -0.1700
Data Index: 2798255 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.5008. Min Act: -0.1700
Data Index: 5609933 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1883. Min Range: -7.1883
Max Act: 6.4695. Min Act: -0.1700
Data Index: 270240 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19