Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4391 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.1522. Min Act: -0.1700
Data Index: 3244365 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.1207. Min Act: -0.1700
Data Index: 2673774 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.1364. Min Act: -0.1700
Data Index: 255700 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.1207. Min Act: -0.1700
Data Index: 1707641 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.1207. Min Act: -0.1700
Data Index: 7371367 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.1049. Min Act: -0.1700
Data Index: 3357367 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.1049. Min Act: -0.1700
Data Index: 6235541 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.1049. Min Act: -0.1700
Data Index: 640921 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.1049. Min Act: -0.1700
Data Index: 161427 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.1049. Min Act: -0.1700
Data Index: 3251217 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.0892. Min Act: -0.1700
Data Index: 3342895 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.0892. Min Act: -0.1700
Data Index: 114034 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.0892. Min Act: -0.1700
Data Index: 6254734 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.0892. Min Act: -0.1700
Data Index: 5190188 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.0892. Min Act: -0.1700
Data Index: 8296343 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.1049. Min Act: -0.1700
Data Index: 3630746 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.0892. Min Act: -0.1700
Data Index: 2483207 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.0892. Min Act: -0.1700
Data Index: 4062790 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.0576. Min Act: -0.1700
Data Index: 3930984 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1522. Min Range: -3.1522
Max Act: 3.0734. Min Act: -0.1700
Data Index: 782874 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #19