Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5785 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6859. Min Range: -6.6859
Max Act: 6.6859. Min Act: -0.1700
Data Index: 7827306 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6859. Min Range: -6.6859
Max Act: 6.3734. Min Act: -0.1700
Data Index: 7021012 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6859. Min Range: -6.6859
Max Act: 6.0297. Min Act: -0.1700
Data Index: 8692267 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.9672. Min Act: -0.1700
Data Index: 757476 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.9047. Min Act: -0.1700
Data Index: 3046470 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.9047. Min Act: -0.1700
Data Index: 680408 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.8422. Min Act: -0.1700
Data Index: 6312200 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.8422. Min Act: -0.1700
Data Index: 6463657 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.8109. Min Act: -0.1700
Data Index: 5883356 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.8109. Min Act: -0.1700
Data Index: 1921757 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.8109. Min Act: -0.1700
Data Index: 3118701 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.7797. Min Act: -0.1700
Data Index: 4112883 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.7484. Min Act: -0.1700
Data Index: 1948700 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.7484. Min Act: -0.1700
Data Index: 1305897 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.7484. Min Act: -0.1700
Data Index: 781619 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.7484. Min Act: -0.1700
Data Index: 8004372 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.7172. Min Act: -0.1700
Data Index: 3423716 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.7172. Min Act: -0.1700
Data Index: 6690950 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.7172. Min Act: -0.1700
Data Index: 8696254 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6859. Min Range: -6.6859
Max Act: 5.6859. Min Act: -0.1700
Data Index: 42077 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #19