Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2734 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0273. Min Range: -6.0273
Max Act: 6.0273. Min Act: -0.1700
Data Index: 5536756 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.9336. Min Act: -0.1700
Data Index: 7558677 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.5898. Min Act: -0.1700
Data Index: 8030313 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.5586. Min Act: -0.1700
Data Index: 6064927 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.5273. Min Act: -0.1700
Data Index: 4696095 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.3711. Min Act: -0.1700
Data Index: 1212100 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.3086. Min Act: -0.1700
Data Index: 7102931 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.3086. Min Act: -0.1700
Data Index: 3380055 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.2461. Min Act: -0.1700
Data Index: 3177318 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.2773. Min Act: -0.1700
Data Index: 3895949 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.2148. Min Act: -0.1700
Data Index: 5755774 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.2148. Min Act: -0.1700
Data Index: 5556942 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.1523. Min Act: -0.1700
Data Index: 129289 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.1211. Min Act: -0.1700
Data Index: 5341674 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.1523. Min Act: -0.1700
Data Index: 920644 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.1211. Min Act: -0.1700
Data Index: 8058595 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.1523. Min Act: -0.1700
Data Index: 2844415 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.1211. Min Act: -0.1700
Data Index: 3740240 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.1211. Min Act: -0.1700
Data Index: 8299948 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0273. Min Range: -6.0273
Max Act: 5.0898. Min Act: -0.1700
Data Index: 7055969 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19