Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4722 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8683. Min Range: -7.8683
Max Act: 7.8683. Min Act: -0.1700
Data Index: 5376149 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8683. Min Range: -7.8683
Max Act: 7.4620. Min Act: -0.1700
Data Index: 1787471 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8683. Min Range: -7.8683
Max Act: 7.3370. Min Act: -0.1700
Data Index: 4402368 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8683. Min Range: -7.8683
Max Act: 7.2120. Min Act: -0.1700
Data Index: 748310 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8683. Min Range: -7.8683
Max Act: 7.1808. Min Act: -0.1700
Data Index: 275176 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8683. Min Range: -7.8683
Max Act: 7.0558. Min Act: -0.1700
Data Index: 4760242 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8683. Min Range: -7.8683
Max Act: 7.0558. Min Act: -0.1700
Data Index: 8421041 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.9933. Min Act: -0.1700
Data Index: 2703531 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.9620. Min Act: -0.1700
Data Index: 8194719 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.8995. Min Act: -0.1700
Data Index: 1320001 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.9308. Min Act: -0.1700
Data Index: 4990817 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.8995. Min Act: -0.1700
Data Index: 6816119 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.9308. Min Act: -0.1700
Data Index: 4410870 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.9308. Min Act: -0.1700
Data Index: 4394682 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.8995. Min Act: -0.1700
Data Index: 6816123 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.8995. Min Act: -0.1700
Data Index: 1991015 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.8995. Min Act: -0.1700
Data Index: 5194420 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.8683. Min Act: -0.1700
Data Index: 5594618 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.8683. Min Act: -0.1700
Data Index: 1563622 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8683. Min Range: -7.8683
Max Act: 6.8370. Min Act: -0.1700
Data Index: 1504262 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19