Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2680 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.4928. Min Act: -0.1700
Data Index: 3760246 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.4928. Min Act: -0.1700
Data Index: 8187769 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.4928. Min Act: -0.1700
Data Index: 641709 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.4615. Min Act: -0.1700
Data Index: 8429687 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.4303. Min Act: -0.1700
Data Index: 8563360 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3990. Min Act: -0.1700
Data Index: 1319950 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.4303. Min Act: -0.1700
Data Index: 5353071 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3990. Min Act: -0.1700
Data Index: 7626042 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3678. Min Act: -0.1700
Data Index: 2185615 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3678. Min Act: -0.1700
Data Index: 7192077 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3678. Min Act: -0.1700
Data Index: 880807 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3990. Min Act: -0.1700
Data Index: 3159911 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3678. Min Act: -0.1700
Data Index: 3104633 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3365. Min Act: -0.1700
Data Index: 7613499 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3053. Min Act: -0.1700
Data Index: 6130977 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3053. Min Act: -0.1700
Data Index: 1944483 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3053. Min Act: -0.1700
Data Index: 1043945 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3053. Min Act: -0.1700
Data Index: 3115349 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3053. Min Act: -0.1700
Data Index: 1149600 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4928. Min Range: -5.4928
Max Act: 5.3053. Min Act: -0.1700
Data Index: 8425148 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19