Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.3839. Min Act: -0.1700
Data Index: 232300 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.2276. Min Act: -0.1700
Data Index: 4348960 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.1651. Min Act: -0.1700
Data Index: 3305526 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.1339. Min Act: -0.1700
Data Index: 6549041 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.1651. Min Act: -0.1700
Data Index: 8302445 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.1026. Min Act: -0.1700
Data Index: 7968653 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.0714. Min Act: -0.1700
Data Index: 7691968 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.0401. Min Act: -0.1700
Data Index: 6538091 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.0401. Min Act: -0.1700
Data Index: 3706278 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.0401. Min Act: -0.1700
Data Index: 3293185 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.0401. Min Act: -0.1700
Data Index: 4303568 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.0089. Min Act: -0.1700
Data Index: 3011772 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3839. Min Range: -6.3839
Max Act: 5.9776. Min Act: -0.1700
Data Index: 1634568 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3839. Min Range: -6.3839
Max Act: 5.9776. Min Act: -0.1700
Data Index: 163158 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3839. Min Range: -6.3839
Max Act: 6.0089. Min Act: -0.1700
Data Index: 2072974 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3839. Min Range: -6.3839
Max Act: 5.9776. Min Act: -0.1700
Data Index: 8635940 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3839. Min Range: -6.3839
Max Act: 5.9464. Min Act: -0.1700
Data Index: 5788717 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3839. Min Range: -6.3839
Max Act: 5.9464. Min Act: -0.1700
Data Index: 6213873 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3839. Min Range: -6.3839
Max Act: 5.9464. Min Act: -0.1700
Data Index: 4559100 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3839. Min Range: -6.3839
Max Act: 5.9464. Min Act: -0.1700
Data Index: 6535785 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #19