Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1742 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1981. Min Range: -5.1981
Max Act: 5.1981. Min Act: -0.1700
Data Index: 4539838 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1981. Min Range: -5.1981
Max Act: 5.1356. Min Act: -0.1700
Data Index: 3861291 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1981. Min Range: -5.1981
Max Act: 5.0731. Min Act: -0.1700
Data Index: 176233 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1981. Min Range: -5.1981
Max Act: 5.0731. Min Act: -0.1700
Data Index: 5267513 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1981. Min Range: -5.1981
Max Act: 5.0106. Min Act: -0.1700
Data Index: 233262 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.9481. Min Act: -0.1700
Data Index: 1421409 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.9169. Min Act: -0.1700
Data Index: 2014961 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.8856. Min Act: -0.1700
Data Index: 8340111 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.8544. Min Act: -0.1700
Data Index: 7795859 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.9169. Min Act: -0.1700
Data Index: 8340104 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.8544. Min Act: -0.1700
Data Index: 2164235 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.8231. Min Act: -0.1700
Data Index: 3708302 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.8231. Min Act: -0.1700
Data Index: 1280642 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.8231. Min Act: -0.1700
Data Index: 7978695 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.7919. Min Act: -0.1700
Data Index: 929078 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.7919. Min Act: -0.1700
Data Index: 3601486 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.7919. Min Act: -0.1700
Data Index: 4729487 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.7919. Min Act: -0.1700
Data Index: 8012386 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.7919. Min Act: -0.1700
Data Index: 8340110 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1981. Min Range: -5.1981
Max Act: 4.7606. Min Act: -0.1700
Data Index: 2656232 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19