Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0859. Min Range: -5.0859
Max Act: 5.0859. Min Act: -0.1700
Data Index: 6945827 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.9921. Min Act: -0.1700
Data Index: 1617052 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.8046. Min Act: -0.1700
Data Index: 4090474 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.7734. Min Act: -0.1700
Data Index: 6286859 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.7734. Min Act: -0.1700
Data Index: 215888 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.7421. Min Act: -0.1700
Data Index: 5548967 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.7421. Min Act: -0.1700
Data Index: 3993438 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.7421. Min Act: -0.1700
Data Index: 1945512 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.7109. Min Act: -0.1700
Data Index: 5912411 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.7109. Min Act: -0.1700
Data Index: 5060801 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.6796. Min Act: -0.1700
Data Index: 3864221 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.6796. Min Act: -0.1700
Data Index: 6875816 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.7109. Min Act: -0.1700
Data Index: 2773542 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.6796. Min Act: -0.1700
Data Index: 7333858 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.6796. Min Act: -0.1700
Data Index: 1742829 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.6484. Min Act: -0.1700
Data Index: 1078368 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.6484. Min Act: -0.1700
Data Index: 1193168 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.6484. Min Act: -0.1700
Data Index: 3461622 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.6484. Min Act: -0.1700
Data Index: 5002844 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0859. Min Range: -5.0859
Max Act: 4.6484. Min Act: -0.1700
Data Index: 3664878 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19