Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.9157. Min Act: -0.1700
Data Index: 4328604 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.9157. Min Act: -0.1700
Data Index: 3900762 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.8532. Min Act: -0.1700
Data Index: 1299945 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.8532. Min Act: -0.1700
Data Index: 4137994 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.7907. Min Act: -0.1700
Data Index: 5761743 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.7594. Min Act: -0.1700
Data Index: 6408157 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.7594. Min Act: -0.1700
Data Index: 8261990 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.7282. Min Act: -0.1700
Data Index: 4436424 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.7282. Min Act: -0.1700
Data Index: 2000616 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.6969. Min Act: -0.1700
Data Index: 7543026 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.6969. Min Act: -0.1700
Data Index: 238944 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.6969. Min Act: -0.1700
Data Index: 6408158 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.6657. Min Act: -0.1700
Data Index: 4003200 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.6657. Min Act: -0.1700
Data Index: 6136760 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.6657. Min Act: -0.1700
Data Index: 2514506 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.6657. Min Act: -0.1700
Data Index: 33150 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.6032. Min Act: -0.1700
Data Index: 6986311 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.6344. Min Act: -0.1700
Data Index: 2416700 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.6344. Min Act: -0.1700
Data Index: 4372763 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9157. Min Range: -5.9157
Max Act: 5.6344. Min Act: -0.1700
Data Index: 4938527 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19