Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5651 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4871. Min Range: -8.4871
Max Act: 8.4871. Min Act: -0.1700
Data Index: 1251472 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4871. Min Range: -8.4871
Max Act: 8.4246. Min Act: -0.1700
Data Index: 1889600 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4871. Min Range: -8.4871
Max Act: 8.1121. Min Act: -0.1700
Data Index: 6214661 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4871. Min Range: -8.4871
Max Act: 8.0496. Min Act: -0.1700
Data Index: 3733556 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.9246. Min Act: -0.1700
Data Index: 5423197 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.9246. Min Act: -0.1700
Data Index: 5690032 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.8621. Min Act: -0.1700
Data Index: 3272076 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.8621. Min Act: -0.1700
Data Index: 3638443 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.8621. Min Act: -0.1700
Data Index: 6512242 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.8621. Min Act: -0.1700
Data Index: 1212983 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.7996. Min Act: -0.1700
Data Index: 5305640 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.7996. Min Act: -0.1700
Data Index: 3874491 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.7996. Min Act: -0.1700
Data Index: 5724812 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.7996. Min Act: -0.1700
Data Index: 674185 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.7371. Min Act: -0.1700
Data Index: 4911395 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.7371. Min Act: -0.1700
Data Index: 1697584 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.7371. Min Act: -0.1700
Data Index: 470684 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.6746. Min Act: -0.1700
Data Index: 6654047 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.7371. Min Act: -0.1700
Data Index: 332832 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4871. Min Range: -8.4871
Max Act: 7.7371. Min Act: -0.1700
Data Index: 4048291 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19