Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2328 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.2842. Min Act: -0.1700
Data Index: 6852203 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.1905. Min Act: -0.1700
Data Index: 8564838 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.1592. Min Act: -0.1700
Data Index: 3413682 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.1592. Min Act: -0.1700
Data Index: 867274 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.1280. Min Act: -0.1687
Data Index: 5634785 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0967. Min Act: -0.1700
Data Index: 1043048 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0967. Min Act: -0.1700
Data Index: 8790402 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0967. Min Act: -0.1700
Data Index: 7713972 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0967. Min Act: -0.1700
Data Index: 1091122 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0967. Min Act: -0.1700
Data Index: 2430052 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0967. Min Act: -0.1700
Data Index: 5775590 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0342. Min Act: -0.1700
Data Index: 5397017 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0342. Min Act: -0.1700
Data Index: 4395174 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0342. Min Act: -0.1699
Data Index: 8788215 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0342. Min Act: -0.1700
Data Index: 2743484 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0342. Min Act: -0.1700
Data Index: 7745267 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0655. Min Act: -0.1700
Data Index: 6208128 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0030. Min Act: -0.1700
Data Index: 4930917 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2842. Min Range: -6.2842
Max Act: 5.9717. Min Act: -0.1700
Data Index: 8085611 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2842. Min Range: -6.2842
Max Act: 6.0030. Min Act: -0.1700
Data Index: 8450111 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19