Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3685 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.3290. Min Act: -0.1700
Data Index: 4128195 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.2348. Min Act: -0.1700
Data Index: 7063716 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1876. Min Act: -0.1700
Data Index: 5647815 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1876. Min Act: -0.1700
Data Index: 1275934 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1876. Min Act: -0.1700
Data Index: 2158154 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1719. Min Act: -0.1700
Data Index: 4945070 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1719. Min Act: -0.1700
Data Index: 7328733 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1719. Min Act: -0.1700
Data Index: 816090 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1561. Min Act: -0.1700
Data Index: 7395649 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1561. Min Act: -0.1700
Data Index: 4083566 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1561. Min Act: -0.1700
Data Index: 8211527 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1561. Min Act: -0.1700
Data Index: 8313024 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1404. Min Act: -0.1700
Data Index: 7236138 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1404. Min Act: -0.1700
Data Index: 7541263 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1404. Min Act: -0.1700
Data Index: 2166908 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1404. Min Act: -0.1700
Data Index: 8498584 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1246. Min Act: -0.1700
Data Index: 2131749 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1246. Min Act: -0.1700
Data Index: 1808863 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1246. Min Act: -0.1700
Data Index: 7995430 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3290. Min Range: -3.3290
Max Act: 3.1246. Min Act: -0.1700
Data Index: 8801498 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19