Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4286 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1456. Min Range: -5.1456
Max Act: 5.1456. Min Act: -0.1700
Data Index: 3730034 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1456. Min Range: -5.1456
Max Act: 5.1144. Min Act: -0.1700
Data Index: 5446564 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1456. Min Range: -5.1456
Max Act: 5.0831. Min Act: -0.1700
Data Index: 1120703 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1456. Min Range: -5.1456
Max Act: 5.0831. Min Act: -0.1700
Data Index: 7937431 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.9894. Min Act: -0.1700
Data Index: 1624243 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.9581. Min Act: -0.1700
Data Index: 7447875 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.9581. Min Act: -0.1700
Data Index: 6365912 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.8644. Min Act: -0.1700
Data Index: 283565 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.8019. Min Act: -0.1700
Data Index: 5952713 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.8019. Min Act: -0.1700
Data Index: 1121443 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.7706. Min Act: -0.1700
Data Index: 2460360 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.7394. Min Act: -0.1700
Data Index: 3868262 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.7394. Min Act: -0.1700
Data Index: 498657 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.7081. Min Act: -0.1700
Data Index: 6910863 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.7081. Min Act: -0.1700
Data Index: 5955117 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.7081. Min Act: -0.1700
Data Index: 6374259 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.7081. Min Act: -0.1700
Data Index: 8258920 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.6769. Min Act: -0.1700
Data Index: 8506636 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.6456. Min Act: -0.1700
Data Index: 6642945 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1456. Min Range: -5.1456
Max Act: 4.6144. Min Act: -0.1700
Data Index: 6751105 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19