Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4955 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.7262. Min Act: -0.1700
Data Index: 1251836 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.6950. Min Act: -0.1700
Data Index: 6831531 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.7262. Min Act: -0.1700
Data Index: 5171962 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.6637. Min Act: -0.1700
Data Index: 7684677 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.6637. Min Act: -0.1700
Data Index: 1558421 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.6637. Min Act: -0.1700
Data Index: 1097395 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.6325. Min Act: -0.1700
Data Index: 5269310 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.5700. Min Act: -0.1700
Data Index: 1248673 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.6012. Min Act: -0.1700
Data Index: 648823 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.6012. Min Act: -0.1700
Data Index: 96128 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.5700. Min Act: -0.1700
Data Index: 5732067 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.5700. Min Act: -0.1700
Data Index: 4600213 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.5387. Min Act: -0.1700
Data Index: 8812102 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.5387. Min Act: -0.1700
Data Index: 3002445 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.5387. Min Act: -0.1700
Data Index: 4335982 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.4762. Min Act: -0.1700
Data Index: 3872630 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.5075. Min Act: -0.1700
Data Index: 7175281 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.5075. Min Act: -0.1700
Data Index: 504425 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.4762. Min Act: -0.1700
Data Index: 4696112 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7262. Min Range: -4.7262
Max Act: 4.4762. Min Act: -0.1700
Data Index: 5033635 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19