Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4057 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.9330. Min Act: -0.1700
Data Index: 1360851 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.7767. Min Act: -0.1700
Data Index: 2292096 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.6517. Min Act: -0.1700
Data Index: 8597166 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.6830. Min Act: -0.1700
Data Index: 2453901 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.6517. Min Act: -0.1700
Data Index: 4339166 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.5892. Min Act: -0.1700
Data Index: 6987111 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.5892. Min Act: -0.1700
Data Index: 8610209 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.5580. Min Act: -0.1700
Data Index: 4021295 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.5580. Min Act: -0.1700
Data Index: 1828059 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.4955. Min Act: -0.1700
Data Index: 4268972 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.4955. Min Act: -0.1700
Data Index: 7125635 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.4955. Min Act: -0.1700
Data Index: 6078564 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.4642. Min Act: -0.1700
Data Index: 1637288 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.4642. Min Act: -0.1700
Data Index: 5898013 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.4642. Min Act: -0.1700
Data Index: 2580654 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.4330. Min Act: -0.1700
Data Index: 6072178 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.4017. Min Act: -0.1700
Data Index: 7975623 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.3392. Min Act: -0.1700
Data Index: 1738673 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.3705. Min Act: -0.1700
Data Index: 695877 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9330. Min Range: -5.9330
Max Act: 5.3705. Min Act: -0.1700
Data Index: 1521814 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #19