Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2198. Min Range: -3.2198
Max Act: 3.2041. Min Act: -0.1700
Data Index: 6092331 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2198. Min Range: -3.2198
Max Act: 3.2198. Min Act: -0.1700
Data Index: 1377862 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2198. Min Range: -3.2198
Max Act: 3.1254. Min Act: -0.1700
Data Index: 2177389 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2198. Min Range: -3.2198
Max Act: 3.1096. Min Act: -0.1700
Data Index: 5350443 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2198. Min Range: -3.2198
Max Act: 3.1096. Min Act: -0.1700
Data Index: 4339213 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2198. Min Range: -3.2198
Max Act: 3.0623. Min Act: -0.1700
Data Index: 4817041 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2198. Min Range: -3.2198
Max Act: 3.0466. Min Act: -0.1700
Data Index: 3309082 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2198. Min Range: -3.2198
Max Act: 3.0623. Min Act: -0.1700
Data Index: 5027196 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2198. Min Range: -3.2198
Max Act: 3.0466. Min Act: -0.1700
Data Index: 8327987 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2198. Min Range: -3.2198
Max Act: 3.0466. Min Act: -0.1700
Data Index: 723294 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2198. Min Range: -3.2198
Max Act: 3.0466. Min Act: -0.1700
Data Index: 1765807 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2198. Min Range: -3.2198
Max Act: 3.0466. Min Act: -0.1700
Data Index: 1272709 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2198. Min Range: -3.2198
Max Act: 2.9834. Min Act: -0.1700
Data Index: 7670000 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2198. Min Range: -3.2198
Max Act: 2.9676. Min Act: -0.1700
Data Index: 6213877 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2198. Min Range: -3.2198
Max Act: 2.9834. Min Act: -0.1700
Data Index: 1705104 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2198. Min Range: -3.2198
Max Act: 2.9676. Min Act: -0.1700
Data Index: 1097092 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2198. Min Range: -3.2198
Max Act: 2.9517. Min Act: -0.1700
Data Index: 3542368 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2198. Min Range: -3.2198
Max Act: 2.9676. Min Act: -0.1700
Data Index: 2773321 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2198. Min Range: -3.2198
Max Act: 2.9359. Min Act: -0.1700
Data Index: 1613711 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2198. Min Range: -3.2198
Max Act: 2.9359. Min Act: -0.1700
Data Index: 6689028 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19