Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2748 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4933. Min Range: -7.4933
Max Act: 7.4933. Min Act: -0.1700
Data Index: 858109 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4933. Min Range: -7.4933
Max Act: 7.4308. Min Act: -0.1700
Data Index: 3785868 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4933. Min Range: -7.4933
Max Act: 7.2433. Min Act: -0.1700
Data Index: 1857126 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4933. Min Range: -7.4933
Max Act: 7.1495. Min Act: -0.1700
Data Index: 5161582 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4933. Min Range: -7.4933
Max Act: 7.1183. Min Act: -0.1700
Data Index: 1095741 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4933. Min Range: -7.4933
Max Act: 7.0245. Min Act: -0.1700
Data Index: 5436719 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.9933. Min Act: -0.1700
Data Index: 5001362 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.9308. Min Act: -0.1700
Data Index: 5537920 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.9933. Min Act: -0.1700
Data Index: 1857124 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.9308. Min Act: -0.1700
Data Index: 3573174 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.9620. Min Act: -0.1700
Data Index: 590051 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.9308. Min Act: -0.1700
Data Index: 189168 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.8995. Min Act: -0.1700
Data Index: 8047486 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.8995. Min Act: -0.1700
Data Index: 8535815 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.8995. Min Act: -0.1700
Data Index: 1975527 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.8995. Min Act: -0.1700
Data Index: 5537923 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.8683. Min Act: -0.1700
Data Index: 240046 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.8058. Min Act: -0.1700
Data Index: 5695288 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.7745. Min Act: -0.1700
Data Index: 8335385 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4933. Min Range: -7.4933
Max Act: 6.7745. Min Act: -0.1700
Data Index: 5537922 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19