Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1827 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7171. Min Range: -8.7171
Max Act: 8.7171. Min Act: -0.1623
Data Index: 923623 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7171. Min Range: -8.7171
Max Act: 8.5296. Min Act: -0.1700
Data Index: 923622 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7171. Min Range: -8.7171
Max Act: 8.2796. Min Act: -0.1489
Data Index: 923615 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7171. Min Range: -8.7171
Max Act: 8.1546. Min Act: -0.1688
Data Index: 4587137 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7171. Min Range: -8.7171
Max Act: 8.0921. Min Act: -0.1612
Data Index: 923602 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.9046. Min Act: -0.1450
Data Index: 923614 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.9046. Min Act: -0.1223
Data Index: 1291617 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.8421. Min Act: -0.1686
Data Index: 923617 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.7171. Min Act: -0.1700
Data Index: 923616 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.7171. Min Act: -0.1633
Data Index: 7640484 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.5296. Min Act: -0.1700
Data Index: 923603 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.5296. Min Act: -0.1700
Data Index: 923604 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.5296. Min Act: -0.1700
Data Index: 8186052 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.5296. Min Act: -0.1700
Data Index: 4587136 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.2796. Min Act: -0.1700
Data Index: 6479948 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.2171. Min Act: -0.1700
Data Index: 7640482 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.2171. Min Act: -0.1570
Data Index: 1291616 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.2171. Min Act: -0.1693
Data Index: 923626 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7171. Min Range: -8.7171
Max Act: 7.0296. Min Act: -0.1570
Data Index: 6360008 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7171. Min Range: -8.7171
Max Act: 6.9046. Min Act: -0.1695
Data Index: 923627 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19