Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1596. Min Range: -6.1596
Max Act: 6.1596. Min Act: -0.1700
Data Index: 6779694 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1596. Min Range: -6.1596
Max Act: 6.0971. Min Act: -0.1700
Data Index: 4018811 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1596. Min Range: -6.1596
Max Act: 6.0034. Min Act: -0.1700
Data Index: 7207869 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1596. Min Range: -6.1596
Max Act: 6.0034. Min Act: -0.1700
Data Index: 393040 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.9721. Min Act: -0.1700
Data Index: 3126597 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.9721. Min Act: -0.1700
Data Index: 2515242 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.9409. Min Act: -0.1700
Data Index: 6572202 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.9096. Min Act: -0.1700
Data Index: 2117594 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.9096. Min Act: -0.1700
Data Index: 6572191 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.9096. Min Act: -0.1700
Data Index: 5855095 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.9096. Min Act: -0.1700
Data Index: 224039 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.8471. Min Act: -0.1700
Data Index: 2704097 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.8471. Min Act: -0.1700
Data Index: 6644298 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.8159. Min Act: -0.1700
Data Index: 3908857 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.8159. Min Act: -0.1700
Data Index: 7304391 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.8159. Min Act: -0.1700
Data Index: 838575 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.7534. Min Act: -0.1700
Data Index: 912463 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.7534. Min Act: -0.1700
Data Index: 4904962 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.7221. Min Act: -0.1700
Data Index: 713617 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1596. Min Range: -6.1596
Max Act: 5.7221. Min Act: -0.1700
Data Index: 48586 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #19