Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2022 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3915. Min Range: -6.3915
Max Act: 6.3915. Min Act: -0.1700
Data Index: 996304 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3915. Min Range: -6.3915
Max Act: 6.3602. Min Act: -0.1700
Data Index: 2645029 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3915. Min Range: -6.3915
Max Act: 6.1102. Min Act: -0.1700
Data Index: 6227343 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3915. Min Range: -6.3915
Max Act: 6.0790. Min Act: -0.1700
Data Index: 1080965 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3915. Min Range: -6.3915
Max Act: 6.0165. Min Act: -0.1700
Data Index: 1205000 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.9852. Min Act: -0.1700
Data Index: 6320243 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.9540. Min Act: -0.1700
Data Index: 957523 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.9540. Min Act: -0.1700
Data Index: 7792649 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.9227. Min Act: -0.1700
Data Index: 7947524 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.9227. Min Act: -0.1700
Data Index: 4939113 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.9227. Min Act: -0.1700
Data Index: 1140833 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.8915. Min Act: -0.1700
Data Index: 6157219 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.8602. Min Act: -0.1700
Data Index: 3507841 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.8602. Min Act: -0.1700
Data Index: 4622574 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.8602. Min Act: -0.1700
Data Index: 2513313 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.8290. Min Act: -0.1700
Data Index: 4958620 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.8290. Min Act: -0.1700
Data Index: 6628809 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.8290. Min Act: -0.1700
Data Index: 1101141 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.8290. Min Act: -0.1700
Data Index: 527554 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3915. Min Range: -6.3915
Max Act: 5.8290. Min Act: -0.1700
Data Index: 6758863 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19