Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1927 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6052. Min Range: -6.6052
Max Act: 6.5427. Min Act: -0.1700
Data Index: 6970824 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6052. Min Range: -6.6052
Max Act: 6.6052. Min Act: -0.1700
Data Index: 4338071 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6052. Min Range: -6.6052
Max Act: 6.5740. Min Act: -0.1700
Data Index: 2750249 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6052. Min Range: -6.6052
Max Act: 6.3865. Min Act: -0.1700
Data Index: 263489 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6052. Min Range: -6.6052
Max Act: 6.1365. Min Act: -0.1700
Data Index: 1590128 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6052. Min Range: -6.6052
Max Act: 6.1677. Min Act: -0.1700
Data Index: 7882128 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6052. Min Range: -6.6052
Max Act: 5.9490. Min Act: -0.1700
Data Index: 7882135 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6052. Min Range: -6.6052
Max Act: 6.2615. Min Act: -0.1700
Data Index: 1590129 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6052. Min Range: -6.6052
Max Act: 5.9802. Min Act: -0.1700
Data Index: 8318375 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6052. Min Range: -6.6052
Max Act: 5.8552. Min Act: -0.1700
Data Index: 232575 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6052. Min Range: -6.6052
Max Act: 5.8240. Min Act: -0.1700
Data Index: 3422429 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6052. Min Range: -6.6052
Max Act: 4.3240. Min Act: -0.1700
Data Index: 514194 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6052. Min Range: -6.6052
Max Act: 5.7615. Min Act: -0.1700
Data Index: 1590138 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6052. Min Range: -6.6052
Max Act: 5.7927. Min Act: -0.1700
Data Index: 1532392 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6052. Min Range: -6.6052
Max Act: 5.3865. Min Act: -0.1700
Data Index: 1572575 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6052. Min Range: -6.6052
Max Act: 5.8240. Min Act: -0.1700
Data Index: 5366558 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6052. Min Range: -6.6052
Max Act: 5.6052. Min Act: -0.1700
Data Index: 7847254 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6052. Min Range: -6.6052
Max Act: 5.9177. Min Act: -0.1700
Data Index: 6085272 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6052. Min Range: -6.6052
Max Act: 6.0427. Min Act: -0.1700
Data Index: 5926631 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6052. Min Range: -6.6052
Max Act: 5.5427. Min Act: -0.1700
Data Index: 8013124 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #19