Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 48 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.7855. Min Act: -0.1700
Data Index: 3085651 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.7855. Min Act: -0.1700
Data Index: 4373456 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.7542. Min Act: -0.1700
Data Index: 1320062 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.5667. Min Act: -0.1700
Data Index: 2075062 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.5355. Min Act: -0.1700
Data Index: 5250225 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.5355. Min Act: -0.1700
Data Index: 6829542 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.4105. Min Act: -0.1700
Data Index: 4524760 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.3792. Min Act: -0.1700
Data Index: 37030 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.4105. Min Act: -0.1700
Data Index: 6324218 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.3480. Min Act: -0.1700
Data Index: 5049632 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.3167. Min Act: -0.1700
Data Index: 7046618 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.3480. Min Act: -0.1700
Data Index: 7103341 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.2855. Min Act: -0.1700
Data Index: 6465774 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.2542. Min Act: -0.1700
Data Index: 139795 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.2542. Min Act: -0.1700
Data Index: 7539919 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.1917. Min Act: -0.1700
Data Index: 2840507 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.1917. Min Act: -0.1700
Data Index: 3101025 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.1292. Min Act: -0.1700
Data Index: 1856056 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.1917. Min Act: -0.1700
Data Index: 7936088 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7855. Min Range: -6.7855
Max Act: 6.1605. Min Act: -0.1700
Data Index: 7918241 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19