Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2966 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2865. Min Range: -5.2865
Max Act: 5.2865. Min Act: -0.1700
Data Index: 8500435 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2865. Min Range: -5.2865
Max Act: 5.0990. Min Act: -0.1700
Data Index: 1184438 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2865. Min Range: -5.2865
Max Act: 5.1302. Min Act: -0.1700
Data Index: 6878889 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2865. Min Range: -5.2865
Max Act: 5.0677. Min Act: -0.1700
Data Index: 5988690 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2865. Min Range: -5.2865
Max Act: 5.0677. Min Act: -0.1700
Data Index: 2620315 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2865. Min Range: -5.2865
Max Act: 5.0677. Min Act: -0.1700
Data Index: 5149280 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2865. Min Range: -5.2865
Max Act: 5.0365. Min Act: -0.1700
Data Index: 43470 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2865. Min Range: -5.2865
Max Act: 5.0677. Min Act: -0.1700
Data Index: 2520812 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2865. Min Range: -5.2865
Max Act: 5.0365. Min Act: -0.1700
Data Index: 7971406 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2865. Min Range: -5.2865
Max Act: 5.0365. Min Act: -0.1700
Data Index: 6035783 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2865. Min Range: -5.2865
Max Act: 5.0052. Min Act: -0.1700
Data Index: 3623702 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2865. Min Range: -5.2865
Max Act: 5.0052. Min Act: -0.1700
Data Index: 5588078 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2865. Min Range: -5.2865
Max Act: 4.9740. Min Act: -0.1700
Data Index: 709234 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2865. Min Range: -5.2865
Max Act: 4.9740. Min Act: -0.1700
Data Index: 3478258 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2865. Min Range: -5.2865
Max Act: 4.9740. Min Act: -0.1700
Data Index: 6150540 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2865. Min Range: -5.2865
Max Act: 4.9740. Min Act: -0.1700
Data Index: 1414747 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2865. Min Range: -5.2865
Max Act: 4.9740. Min Act: -0.1700
Data Index: 1245008 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2865. Min Range: -5.2865
Max Act: 4.9427. Min Act: -0.1700
Data Index: 582147 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2865. Min Range: -5.2865
Max Act: 4.9115. Min Act: -0.1700
Data Index: 6326192 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2865. Min Range: -5.2865
Max Act: 4.9115. Min Act: -0.1700
Data Index: 525641 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #19