Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3409 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.7342. Min Act: -0.1700
Data Index: 6691155 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.6717. Min Act: -0.1700
Data Index: 4062960 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.5779. Min Act: -0.1700
Data Index: 2268280 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.5467. Min Act: -0.1700
Data Index: 5984843 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.5779. Min Act: -0.1700
Data Index: 2232912 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.5154. Min Act: -0.1700
Data Index: 4956179 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4842. Min Act: -0.1700
Data Index: 882352 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4842. Min Act: -0.1700
Data Index: 5190463 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4842. Min Act: -0.1700
Data Index: 1104760 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4842. Min Act: -0.1700
Data Index: 4882586 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4217. Min Act: -0.1700
Data Index: 1469639 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4529. Min Act: -0.1700
Data Index: 6186839 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4529. Min Act: -0.1700
Data Index: 3373194 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4529. Min Act: -0.1700
Data Index: 54567 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4217. Min Act: -0.1700
Data Index: 4390425 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4217. Min Act: -0.1700
Data Index: 7130555 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4217. Min Act: -0.1700
Data Index: 1894582 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4217. Min Act: -0.1700
Data Index: 1837063 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.3904. Min Act: -0.1700
Data Index: 1944866 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7342. Min Range: -5.7342
Max Act: 5.4217. Min Act: -0.1700
Data Index: 157447 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19