Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5957 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.9254. Min Act: -0.1700
Data Index: 7068174 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.7691. Min Act: -0.1700
Data Index: 4726052 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.7691. Min Act: -0.1700
Data Index: 8367018 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.7691. Min Act: -0.1700
Data Index: 6907487 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.7378. Min Act: -0.1700
Data Index: 2681908 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.7378. Min Act: -0.1700
Data Index: 5755354 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.7065. Min Act: -0.1700
Data Index: 2140267 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.7065. Min Act: -0.1700
Data Index: 7011019 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.7065. Min Act: -0.1700
Data Index: 2545007 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.7065. Min Act: -0.1700
Data Index: 5193530 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.7065. Min Act: -0.1700
Data Index: 8185205 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.6752. Min Act: -0.1700
Data Index: 8522679 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.6752. Min Act: -0.1700
Data Index: 1427542 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.7065. Min Act: -0.1700
Data Index: 7597159 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.6439. Min Act: -0.1700
Data Index: 3587827 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.6439. Min Act: -0.1700
Data Index: 4127360 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.6439. Min Act: -0.1700
Data Index: 7014312 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.6439. Min Act: -0.1700
Data Index: 1097417 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.6439. Min Act: -0.1700
Data Index: 4910383 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9254. Min Range: -3.9254
Max Act: 3.6439. Min Act: -0.1700
Data Index: 7447100 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19