Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5731 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0895. Min Range: -8.0895
Max Act: 8.0895. Min Act: -0.1700
Data Index: 2798376 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0895. Min Range: -8.0895
Max Act: 7.4332. Min Act: -0.1700
Data Index: 6270506 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0895. Min Range: -8.0895
Max Act: 7.3707. Min Act: -0.1700
Data Index: 5289236 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0895. Min Range: -8.0895
Max Act: 7.3395. Min Act: -0.1700
Data Index: 7083255 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0895. Min Range: -8.0895
Max Act: 7.3395. Min Act: -0.1700
Data Index: 1812251 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0895. Min Range: -8.0895
Max Act: 7.2457. Min Act: -0.1700
Data Index: 2400099 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0895. Min Range: -8.0895
Max Act: 7.1207. Min Act: -0.1700
Data Index: 5399434 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0895. Min Range: -8.0895
Max Act: 7.0270. Min Act: -0.1700
Data Index: 5057736 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0895. Min Range: -8.0895
Max Act: 7.0582. Min Act: -0.1700
Data Index: 8214229 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0895. Min Range: -8.0895
Max Act: 6.9957. Min Act: -0.1700
Data Index: 3135949 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0895. Min Range: -8.0895
Max Act: 6.9957. Min Act: -0.1700
Data Index: 7821056 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0895. Min Range: -8.0895
Max Act: 6.9957. Min Act: -0.1700
Data Index: 8372971 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0895. Min Range: -8.0895
Max Act: 6.9332. Min Act: -0.1700
Data Index: 180858 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0895. Min Range: -8.0895
Max Act: 6.9020. Min Act: -0.1700
Data Index: 4184518 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0895. Min Range: -8.0895
Max Act: 6.9020. Min Act: -0.1700
Data Index: 6899682 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0895. Min Range: -8.0895
Max Act: 6.8707. Min Act: -0.1700
Data Index: 6894981 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0895. Min Range: -8.0895
Max Act: 6.8707. Min Act: -0.1700
Data Index: 6940693 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0895. Min Range: -8.0895
Max Act: 6.8395. Min Act: -0.1700
Data Index: 2749919 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0895. Min Range: -8.0895
Max Act: 6.8395. Min Act: -0.1700
Data Index: 1109517 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0895. Min Range: -8.0895
Max Act: 6.8707. Min Act: -0.1700
Data Index: 7142858 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19