Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4276 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.3852. Min Act: -0.1700
Data Index: 8190241 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.3227. Min Act: -0.1700
Data Index: 2870106 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.3227. Min Act: -0.1700
Data Index: 997967 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.1664. Min Act: -0.1700
Data Index: 7474397 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.0414. Min Act: -0.1700
Data Index: 3353232 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3852. Min Range: -7.3852
Max Act: 7.0102. Min Act: -0.1700
Data Index: 7958471 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.9789. Min Act: -0.1700
Data Index: 1338069 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.9477. Min Act: -0.1700
Data Index: 958939 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.9164. Min Act: -0.1700
Data Index: 1686614 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.8852. Min Act: -0.1700
Data Index: 2200006 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.8852. Min Act: -0.1700
Data Index: 4749774 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.7914. Min Act: -0.1700
Data Index: 3633008 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.7914. Min Act: -0.1700
Data Index: 2854654 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.7602. Min Act: -0.1700
Data Index: 3147303 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.7602. Min Act: -0.1700
Data Index: 7436123 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.7602. Min Act: -0.1700
Data Index: 3834972 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.7289. Min Act: -0.1700
Data Index: 2854643 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.7289. Min Act: -0.1700
Data Index: 6861376 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.6977. Min Act: -0.1700
Data Index: 4815372 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3852. Min Range: -7.3852
Max Act: 6.6977. Min Act: -0.1700
Data Index: 4080638 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19