Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1288. Min Range: -5.1288
Max Act: 5.1288. Min Act: -0.1700
Data Index: 1250900 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1288. Min Range: -5.1288
Max Act: 5.1288. Min Act: -0.1700
Data Index: 2588570 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1288. Min Range: -5.1288
Max Act: 5.0351. Min Act: -0.1700
Data Index: 5452381 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1288. Min Range: -5.1288
Max Act: 5.0038. Min Act: -0.1700
Data Index: 4494101 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.9726. Min Act: -0.1700
Data Index: 4096012 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.9726. Min Act: -0.1700
Data Index: 455484 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.9726. Min Act: -0.1700
Data Index: 5566113 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.9101. Min Act: -0.1700
Data Index: 7732395 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.9413. Min Act: -0.1700
Data Index: 8577831 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.9413. Min Act: -0.1700
Data Index: 3291840 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.9101. Min Act: -0.1700
Data Index: 6123905 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.9413. Min Act: -0.1700
Data Index: 5126894 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.9101. Min Act: -0.1700
Data Index: 6850112 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.8788. Min Act: -0.1700
Data Index: 24881 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.9101. Min Act: -0.1700
Data Index: 8516450 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.8788. Min Act: -0.1700
Data Index: 8714773 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.8788. Min Act: -0.1700
Data Index: 7137230 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.8476. Min Act: -0.1700
Data Index: 5019811 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.8476. Min Act: -0.1700
Data Index: 2108989 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1288. Min Range: -5.1288
Max Act: 4.8476. Min Act: -0.1700
Data Index: 337475 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #19