Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4738 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.6628. Min Act: -0.1700
Data Index: 4061413 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.6628. Min Act: -0.1700
Data Index: 4061410 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.6628. Min Act: -0.1700
Data Index: 2220153 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.6628. Min Act: -0.1700
Data Index: 6769541 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.6316. Min Act: -0.1700
Data Index: 6769557 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.6003. Min Act: -0.1700
Data Index: 6769555 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.6003. Min Act: -0.1700
Data Index: 6769550 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.5691. Min Act: -0.1700
Data Index: 2364353 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.5691. Min Act: -0.1700
Data Index: 4269166 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.5691. Min Act: -0.1700
Data Index: 6769552 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.5378. Min Act: -0.1700
Data Index: 4061422 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.5378. Min Act: -0.1700
Data Index: 6769543 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.5378. Min Act: -0.1700
Data Index: 724069 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.5378. Min Act: -0.1700
Data Index: 7424252 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.5066. Min Act: -0.1700
Data Index: 2220151 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.5066. Min Act: -0.1700
Data Index: 6769551 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.4753. Min Act: -0.1700
Data Index: 8735394 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.4441. Min Act: -0.1700
Data Index: 2220149 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.4753. Min Act: -0.1700
Data Index: 6604790 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6628. Min Range: -5.6628
Max Act: 5.4441. Min Act: -0.1700
Data Index: 4812878 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19