Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3254 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3750. Min Range: -6.3750
Max Act: 6.3750. Min Act: -0.1700
Data Index: 247100 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3750. Min Range: -6.3750
Max Act: 6.3125. Min Act: -0.1700
Data Index: 5919534 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3750. Min Range: -6.3750
Max Act: 6.0000. Min Act: -0.1700
Data Index: 6320124 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.9375. Min Act: -0.1700
Data Index: 6026397 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.8438. Min Act: -0.1700
Data Index: 2388390 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.8438. Min Act: -0.1700
Data Index: 631355 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.8438. Min Act: -0.1700
Data Index: 825455 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.8750. Min Act: -0.1700
Data Index: 4005345 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.8125. Min Act: -0.1700
Data Index: 8324055 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.7813. Min Act: -0.1700
Data Index: 5754625 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.7188. Min Act: -0.1700
Data Index: 4776120 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.7500. Min Act: -0.1700
Data Index: 2466983 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.7500. Min Act: -0.1700
Data Index: 5635153 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.7500. Min Act: -0.1700
Data Index: 5126281 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.6875. Min Act: -0.1700
Data Index: 2341129 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.7188. Min Act: -0.1700
Data Index: 5681260 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.7188. Min Act: -0.1700
Data Index: 4034468 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.7188. Min Act: -0.1700
Data Index: 4905138 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.6875. Min Act: -0.1700
Data Index: 3132461 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3750. Min Range: -6.3750
Max Act: 5.6875. Min Act: -0.1700
Data Index: 3306611 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19