Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2662 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0461. Min Range: -6.0461
Max Act: 6.0461. Min Act: -0.1700
Data Index: 5461014 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.9211. Min Act: -0.1700
Data Index: 3557418 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.8898. Min Act: -0.1700
Data Index: 6511855 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.8898. Min Act: -0.1700
Data Index: 2153190 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.8898. Min Act: -0.1700
Data Index: 3325975 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.8586. Min Act: -0.1700
Data Index: 3968634 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.8586. Min Act: -0.1700
Data Index: 970725 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.8273. Min Act: -0.1700
Data Index: 1051845 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.7961. Min Act: -0.1700
Data Index: 432360 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.7961. Min Act: -0.1700
Data Index: 1934670 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.7648. Min Act: -0.1700
Data Index: 4430561 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.7336. Min Act: -0.1700
Data Index: 1301678 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.7336. Min Act: -0.1700
Data Index: 5824330 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.7336. Min Act: -0.1700
Data Index: 2452788 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.7336. Min Act: -0.1700
Data Index: 3243393 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.7023. Min Act: -0.1700
Data Index: 1559989 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.7023. Min Act: -0.1700
Data Index: 5340894 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.7023. Min Act: -0.1700
Data Index: 6259814 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.7023. Min Act: -0.1700
Data Index: 1273835 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0461. Min Range: -6.0461
Max Act: 5.6711. Min Act: -0.1700
Data Index: 3234927 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19