Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3692 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1731. Min Range: -4.1731
Max Act: 4.1731. Min Act: -0.1700
Data Index: 835927 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1731. Min Range: -4.1731
Max Act: 4.1106. Min Act: -0.1700
Data Index: 6613222 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.9230. Min Act: -0.1700
Data Index: 2963268 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.9230. Min Act: -0.1700
Data Index: 8119134 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.8605. Min Act: -0.1700
Data Index: 200008 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.8605. Min Act: -0.1700
Data Index: 5671734 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.8448. Min Act: -0.1700
Data Index: 1389634 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.8448. Min Act: -0.1700
Data Index: 4716496 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.8448. Min Act: -0.1700
Data Index: 6733455 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.8136. Min Act: -0.1700
Data Index: 1439527 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.7823. Min Act: -0.1700
Data Index: 7335798 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.7510. Min Act: -0.1700
Data Index: 6394526 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.7354. Min Act: -0.1700
Data Index: 6719423 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.7354. Min Act: -0.1700
Data Index: 4650437 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.7197. Min Act: -0.1700
Data Index: 4153506 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.7041. Min Act: -0.1700
Data Index: 3220285 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.7041. Min Act: -0.1700
Data Index: 6047581 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.7041. Min Act: -0.1700
Data Index: 5456248 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.6885. Min Act: -0.1700
Data Index: 6219439 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1731. Min Range: -4.1731
Max Act: 3.6728. Min Act: -0.1700
Data Index: 1676970 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19