Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1452 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.7262. Min Act: -0.1700
Data Index: 556330 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.7262. Min Act: -0.1700
Data Index: 948800 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6949. Min Act: -0.1700
Data Index: 6483940 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6636. Min Act: -0.1700
Data Index: 2699546 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6636. Min Act: -0.1700
Data Index: 7937504 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6010. Min Act: -0.1700
Data Index: 7951516 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6323. Min Act: -0.1700
Data Index: 8571189 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6323. Min Act: -0.1700
Data Index: 4218857 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6323. Min Act: -0.1700
Data Index: 4328323 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6636. Min Act: -0.1700
Data Index: 2060748 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6323. Min Act: -0.1700
Data Index: 2918171 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6010. Min Act: -0.1700
Data Index: 3692681 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6010. Min Act: -0.1700
Data Index: 3736503 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6010. Min Act: -0.1700
Data Index: 4373056 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6010. Min Act: -0.1700
Data Index: 5005931 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6010. Min Act: -0.1700
Data Index: 5420630 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6010. Min Act: -0.1700
Data Index: 5436763 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6010. Min Act: -0.1700
Data Index: 5863232 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6010. Min Act: -0.1700
Data Index: 5917075 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7262. Min Range: -3.7262
Max Act: 3.6010. Min Act: -0.1700
Data Index: 6061821 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19