Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3945 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1813. Min Range: -7.1813
Max Act: 7.1813. Min Act: -0.1700
Data Index: 5185008 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.6813. Min Act: -0.1700
Data Index: 8376339 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.6500. Min Act: -0.1700
Data Index: 8466550 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.5563. Min Act: -0.1700
Data Index: 1044499 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.5875. Min Act: -0.1700
Data Index: 8534071 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.5250. Min Act: -0.1700
Data Index: 333884 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.5250. Min Act: -0.1700
Data Index: 4326028 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.5250. Min Act: -0.1700
Data Index: 277702 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.4938. Min Act: -0.1700
Data Index: 7602564 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.4625. Min Act: -0.1700
Data Index: 8145149 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.4313. Min Act: -0.1700
Data Index: 2394128 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.4313. Min Act: -0.1700
Data Index: 5648965 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.4313. Min Act: -0.1700
Data Index: 6216077 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.4313. Min Act: -0.1700
Data Index: 1181341 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.4313. Min Act: -0.1700
Data Index: 6475558 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.4313. Min Act: -0.1700
Data Index: 8193184 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.4000. Min Act: -0.1700
Data Index: 7761416 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.4000. Min Act: -0.1700
Data Index: 5840252 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.4313. Min Act: -0.1700
Data Index: 2060333 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1813. Min Range: -7.1813
Max Act: 6.3375. Min Act: -0.1700
Data Index: 1392028 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19