Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5691 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0339. Min Range: -4.0339
Max Act: 4.0339. Min Act: -0.1700
Data Index: 4805625 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0339. Min Range: -4.0339
Max Act: 4.0026. Min Act: -0.1700
Data Index: 8266761 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.9713. Min Act: -0.1700
Data Index: 6248174 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.9713. Min Act: -0.1700
Data Index: 5344748 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8775. Min Act: -0.1700
Data Index: 1072110 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8619. Min Act: -0.1700
Data Index: 8035884 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8619. Min Act: -0.1700
Data Index: 6070201 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8463. Min Act: -0.1700
Data Index: 1678883 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8463. Min Act: -0.1700
Data Index: 8271840 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8463. Min Act: -0.1700
Data Index: 7806709 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8463. Min Act: -0.1700
Data Index: 7544039 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8306. Min Act: -0.1700
Data Index: 4062656 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8150. Min Act: -0.1700
Data Index: 7843322 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.8306. Min Act: -0.1700
Data Index: 7793513 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.7681. Min Act: -0.1700
Data Index: 7180716 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.7837. Min Act: -0.1700
Data Index: 2878108 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.7681. Min Act: -0.1700
Data Index: 945328 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.7837. Min Act: -0.1700
Data Index: 46256 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.7837. Min Act: -0.1700
Data Index: 8161447 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0339. Min Range: -4.0339
Max Act: 3.7837. Min Act: -0.1700
Data Index: 6217010 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19