Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4047 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.7921. Min Act: -0.1700
Data Index: 4257860 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.6671. Min Act: -0.1700
Data Index: 6783357 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.5421. Min Act: -0.1700
Data Index: 3580799 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.5421. Min Act: -0.1700
Data Index: 3719373 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.5733. Min Act: -0.1700
Data Index: 3730583 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.5421. Min Act: -0.1700
Data Index: 3339072 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.4796. Min Act: -0.1700
Data Index: 3528096 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.4796. Min Act: -0.1700
Data Index: 2289783 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.4483. Min Act: -0.1700
Data Index: 6189471 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.4171. Min Act: -0.1700
Data Index: 8415301 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.4171. Min Act: -0.1700
Data Index: 3774324 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.3858. Min Act: -0.1700
Data Index: 1216897 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.3858. Min Act: -0.1700
Data Index: 1453449 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.4171. Min Act: -0.1700
Data Index: 563904 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.3858. Min Act: -0.1700
Data Index: 4549811 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.3546. Min Act: -0.1700
Data Index: 3938255 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.2921. Min Act: -0.1700
Data Index: 8620464 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.2608. Min Act: -0.1700
Data Index: 281341 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.2608. Min Act: -0.1700
Data Index: 8259572 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7921. Min Range: -6.7921
Max Act: 6.2296. Min Act: -0.1700
Data Index: 4711723 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19