Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2945 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.9989. Min Act: -0.1700
Data Index: 1589489 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.9989. Min Act: -0.1700
Data Index: 1589472 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.5926. Min Act: -0.1700
Data Index: 1426899 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.5926. Min Act: -0.1700
Data Index: 594639 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.4989. Min Act: -0.1700
Data Index: 3237886 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.4989. Min Act: -0.1700
Data Index: 2494269 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.4676. Min Act: -0.1700
Data Index: 3176695 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.4989. Min Act: -0.1700
Data Index: 7157370 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.4676. Min Act: -0.1700
Data Index: 8055923 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.4051. Min Act: -0.1700
Data Index: 1090730 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.4051. Min Act: -0.1700
Data Index: 5992654 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.4364. Min Act: -0.1700
Data Index: 7970197 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.4051. Min Act: -0.1700
Data Index: 4120504 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.3739. Min Act: -0.1700
Data Index: 4667526 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.3739. Min Act: -0.1700
Data Index: 6060205 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.3426. Min Act: -0.1700
Data Index: 6523401 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.2801. Min Act: -0.1700
Data Index: 6061183 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.3114. Min Act: -0.1700
Data Index: 5755663 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.2801. Min Act: -0.1700
Data Index: 2625143 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9989. Min Range: -4.9989
Max Act: 4.3114. Min Act: -0.1700
Data Index: 896867 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19