Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 595 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.9363. Min Act: -0.1700
Data Index: 294885 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.9051. Min Act: -0.1700
Data Index: 1209792 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.9051. Min Act: -0.1700
Data Index: 3521945 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8738. Min Act: -0.1700
Data Index: 7341777 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8425. Min Act: -0.1700
Data Index: 6486003 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8738. Min Act: -0.1700
Data Index: 79954 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.9051. Min Act: -0.1700
Data Index: 5134922 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8738. Min Act: -0.1700
Data Index: 4743070 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8425. Min Act: -0.1700
Data Index: 2613449 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8738. Min Act: -0.1700
Data Index: 2429481 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.9051. Min Act: -0.1700
Data Index: 8308104 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8738. Min Act: -0.1700
Data Index: 7889975 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.6861. Min Act: -0.1700
Data Index: 651887 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8425. Min Act: -0.1700
Data Index: 472124 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8113. Min Act: -0.1700
Data Index: 2396125 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8425. Min Act: -0.1700
Data Index: 3091262 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8425. Min Act: -0.1700
Data Index: 4488379 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8425. Min Act: -0.1700
Data Index: 6026659 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8113. Min Act: -0.1700
Data Index: 6245994 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9363. Min Range: -3.9363
Max Act: 3.8425. Min Act: -0.1700
Data Index: 6923481 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19