Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4050 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2129. Min Range: -6.2129
Max Act: 6.2129. Min Act: -0.1700
Data Index: 6519612 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2129. Min Range: -6.2129
Max Act: 6.1816. Min Act: -0.1700
Data Index: 1569493 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2129. Min Range: -6.2129
Max Act: 6.1504. Min Act: -0.1700
Data Index: 8776144 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.9629. Min Act: -0.1700
Data Index: 6899464 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.9316. Min Act: -0.1700
Data Index: 5936255 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.9004. Min Act: -0.1700
Data Index: 6946316 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.9316. Min Act: -0.1700
Data Index: 1196814 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.7754. Min Act: -0.1700
Data Index: 5579547 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.7754. Min Act: -0.1700
Data Index: 3368176 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.7441. Min Act: -0.1700
Data Index: 7536032 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.6816. Min Act: -0.1700
Data Index: 4899330 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.6504. Min Act: -0.1700
Data Index: 2134011 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.6504. Min Act: -0.1700
Data Index: 3317444 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.6504. Min Act: -0.1700
Data Index: 7270513 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.6191. Min Act: -0.1700
Data Index: 1291642 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.6191. Min Act: -0.1700
Data Index: 4970736 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.6191. Min Act: -0.1700
Data Index: 5309475 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.5879. Min Act: -0.1700
Data Index: 7806513 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.5879. Min Act: -0.1700
Data Index: 6648103 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2129. Min Range: -6.2129
Max Act: 5.5879. Min Act: -0.1700
Data Index: 6318731 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19