Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 216 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.3404. Min Act: -0.1700
Data Index: 3048362 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.2416. Min Act: -0.1700
Data Index: 7583284 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.2416. Min Act: -0.1700
Data Index: 194231 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.2416. Min Act: -0.1700
Data Index: 2322025 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.2416. Min Act: -0.1700
Data Index: 3025829 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.2250. Min Act: -0.1700
Data Index: 5316950 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.2084. Min Act: -0.1698
Data Index: 1012078 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.2084. Min Act: -0.1700
Data Index: 8650831 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.2084. Min Act: -0.1700
Data Index: 3047322 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.1919. Min Act: -0.1700
Data Index: 7275665 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.1586. Min Act: -0.1700
Data Index: 3091992 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.1419. Min Act: -0.1700
Data Index: 4903988 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.1419. Min Act: -0.1700
Data Index: 8116877 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.1252. Min Act: -0.1696
Data Index: 8675597 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.1252. Min Act: -0.1700
Data Index: 5289260 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.1252. Min Act: -0.1700
Data Index: 8414042 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.1085. Min Act: -0.1700
Data Index: 3045091 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.1085. Min Act: -0.1700
Data Index: 6860267 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.1085. Min Act: -0.1700
Data Index: 4720478 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3404. Min Range: -2.3404
Max Act: 2.1085. Min Act: -0.1700
Data Index: 3259553 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19