Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5287 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1571. Min Range: -5.1571
Max Act: 5.1571. Min Act: -0.1700
Data Index: 7942950 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.6571. Min Act: -0.1700
Data Index: 6124047 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.6259. Min Act: -0.1700
Data Index: 5258496 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.6259. Min Act: -0.1700
Data Index: 4406235 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.5321. Min Act: -0.1700
Data Index: 3261595 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.5009. Min Act: -0.1700
Data Index: 687622 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.5009. Min Act: -0.1700
Data Index: 5137360 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.4696. Min Act: -0.1700
Data Index: 1329402 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.4384. Min Act: -0.1700
Data Index: 6068324 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.4071. Min Act: -0.1700
Data Index: 8473431 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.4071. Min Act: -0.1700
Data Index: 2909489 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.4384. Min Act: -0.1700
Data Index: 5764759 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.4071. Min Act: -0.1700
Data Index: 8725371 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.4071. Min Act: -0.1700
Data Index: 953100 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.3759. Min Act: -0.1700
Data Index: 3831228 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.3759. Min Act: -0.1700
Data Index: 4848601 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.3759. Min Act: -0.1700
Data Index: 1876127 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.3759. Min Act: -0.1700
Data Index: 1776317 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.3759. Min Act: -0.1700
Data Index: 207800 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1571. Min Range: -5.1571
Max Act: 4.3133. Min Act: -0.1700
Data Index: 4251407 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19