Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4451 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3806. Min Range: -6.3806
Max Act: 6.3806. Min Act: -0.1700
Data Index: 8803431 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3806. Min Range: -6.3806
Max Act: 6.2869. Min Act: -0.1700
Data Index: 5764209 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3806. Min Range: -6.3806
Max Act: 6.2556. Min Act: -0.1700
Data Index: 769050 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3806. Min Range: -6.3806
Max Act: 6.1619. Min Act: -0.1700
Data Index: 4575020 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3806. Min Range: -6.3806
Max Act: 6.1306. Min Act: -0.1700
Data Index: 5645391 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3806. Min Range: -6.3806
Max Act: 6.0994. Min Act: -0.1700
Data Index: 5983864 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3806. Min Range: -6.3806
Max Act: 6.0681. Min Act: -0.1700
Data Index: 3138571 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3806. Min Range: -6.3806
Max Act: 6.0369. Min Act: -0.1700
Data Index: 3138570 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3806. Min Range: -6.3806
Max Act: 6.0369. Min Act: -0.1700
Data Index: 2682529 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3806. Min Range: -6.3806
Max Act: 6.0369. Min Act: -0.1700
Data Index: 2765358 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3806. Min Range: -6.3806
Max Act: 5.9744. Min Act: -0.1700
Data Index: 450758 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3806. Min Range: -6.3806
Max Act: 6.0056. Min Act: -0.1700
Data Index: 5477637 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3806. Min Range: -6.3806
Max Act: 5.9744. Min Act: -0.1700
Data Index: 4245268 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3806. Min Range: -6.3806
Max Act: 5.9744. Min Act: -0.1700
Data Index: 1037234 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3806. Min Range: -6.3806
Max Act: 5.9744. Min Act: -0.1700
Data Index: 5585912 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3806. Min Range: -6.3806
Max Act: 5.9744. Min Act: -0.1700
Data Index: 3021822 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3806. Min Range: -6.3806
Max Act: 5.9431. Min Act: -0.1700
Data Index: 1285721 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3806. Min Range: -6.3806
Max Act: 5.9431. Min Act: -0.1700
Data Index: 1222225 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3806. Min Range: -6.3806
Max Act: 5.9431. Min Act: -0.1700
Data Index: 4072989 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3806. Min Range: -6.3806
Max Act: 5.9119. Min Act: -0.1700
Data Index: 521710 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #19