Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2168 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0837. Min Range: -7.0837
Max Act: 7.0837. Min Act: -0.1700
Data Index: 6574779 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.9899. Min Act: -0.1700
Data Index: 7676786 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.8649. Min Act: -0.1700
Data Index: 3936699 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.8649. Min Act: -0.1700
Data Index: 6148276 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.8337. Min Act: -0.1700
Data Index: 4565049 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.6774. Min Act: -0.1700
Data Index: 8426449 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.7087. Min Act: -0.1700
Data Index: 4244761 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.6774. Min Act: -0.1700
Data Index: 635659 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.6774. Min Act: -0.1700
Data Index: 7764792 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.6774. Min Act: -0.1700
Data Index: 3443122 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.6149. Min Act: -0.1700
Data Index: 4711965 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.5212. Min Act: -0.1700
Data Index: 3985924 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.5212. Min Act: -0.1700
Data Index: 4115463 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.4899. Min Act: -0.1700
Data Index: 7597330 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.5212. Min Act: -0.1700
Data Index: 107494 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.5212. Min Act: -0.1700
Data Index: 3194748 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.4587. Min Act: -0.1700
Data Index: 7200404 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.3962. Min Act: -0.1700
Data Index: 7784192 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.3962. Min Act: -0.1700
Data Index: 4746362 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0837. Min Range: -7.0837
Max Act: 6.4274. Min Act: -0.1700
Data Index: 4439102 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19