Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3555 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1967. Min Range: -7.1967
Max Act: 7.1967. Min Act: -0.1700
Data Index: 2221460 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1967. Min Range: -7.1967
Max Act: 7.1655. Min Act: -0.1700
Data Index: 4416409 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1967. Min Range: -7.1967
Max Act: 7.1030. Min Act: -0.1700
Data Index: 498829 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1967. Min Range: -7.1967
Max Act: 7.0717. Min Act: -0.1700
Data Index: 3277285 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.9780. Min Act: -0.1700
Data Index: 4782130 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.9467. Min Act: -0.1700
Data Index: 2655937 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.9467. Min Act: -0.1700
Data Index: 1291009 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.8842. Min Act: -0.1700
Data Index: 7671315 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.8842. Min Act: -0.1700
Data Index: 1544045 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.9155. Min Act: -0.1700
Data Index: 1502519 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.8842. Min Act: -0.1700
Data Index: 547864 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.8842. Min Act: -0.1700
Data Index: 5924781 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.8530. Min Act: -0.1700
Data Index: 7940281 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.8530. Min Act: -0.1700
Data Index: 5785905 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.8217. Min Act: -0.1700
Data Index: 7138006 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.8217. Min Act: -0.1700
Data Index: 4821337 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.8217. Min Act: -0.1700
Data Index: 2067963 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.8217. Min Act: -0.1700
Data Index: 5213241 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.7905. Min Act: -0.1700
Data Index: 2806673 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1967. Min Range: -7.1967
Max Act: 6.7905. Min Act: -0.1700
Data Index: 300434 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19