Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3584 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1920. Min Range: -4.1920
Max Act: 4.1920. Min Act: -0.1700
Data Index: 7703422 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1920. Min Range: -4.1920
Max Act: 4.1607. Min Act: -0.1700
Data Index: 3689170 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1920. Min Range: -4.1920
Max Act: 4.0670. Min Act: -0.1700
Data Index: 8417895 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1920. Min Range: -4.1920
Max Act: 4.0670. Min Act: -0.1700
Data Index: 3888470 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1920. Min Range: -4.1920
Max Act: 4.0670. Min Act: -0.1700
Data Index: 7306100 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1920. Min Range: -4.1920
Max Act: 4.0044. Min Act: -0.1700
Data Index: 1853758 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.9732. Min Act: -0.1700
Data Index: 3719566 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.9107. Min Act: -0.1700
Data Index: 4837124 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.8794. Min Act: -0.1700
Data Index: 1144934 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.9107. Min Act: -0.1700
Data Index: 2509659 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.9107. Min Act: -0.1700
Data Index: 79858 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.8794. Min Act: -0.1700
Data Index: 388073 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.8481. Min Act: -0.1700
Data Index: 4650407 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.8481. Min Act: -0.1700
Data Index: 1079356 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.8325. Min Act: -0.1700
Data Index: 3002753 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.8168. Min Act: -0.1700
Data Index: 4554300 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.8012. Min Act: -0.1700
Data Index: 8083057 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.8168. Min Act: -0.1700
Data Index: 341126 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.7856. Min Act: -0.1700
Data Index: 5215141 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1920. Min Range: -4.1920
Max Act: 3.8012. Min Act: -0.1700
Data Index: 3922068 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19