Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3879 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.3777. Min Act: -0.1700
Data Index: 186079 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.2207. Min Act: -0.1700
Data Index: 5133412 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.2050. Min Act: -0.1700
Data Index: 7818534 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1892. Min Act: -0.1700
Data Index: 6722203 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.2207. Min Act: -0.1700
Data Index: 5330229 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1892. Min Act: -0.1700
Data Index: 4570421 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1892. Min Act: -0.1700
Data Index: 3714442 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1892. Min Act: -0.1700
Data Index: 5768673 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1735. Min Act: -0.1700
Data Index: 3194773 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1892. Min Act: -0.1700
Data Index: 3363877 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1420. Min Act: -0.1700
Data Index: 6923487 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1420. Min Act: -0.1700
Data Index: 4980398 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1420. Min Act: -0.1700
Data Index: 5875162 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1420. Min Act: -0.1700
Data Index: 1289737 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1420. Min Act: -0.1700
Data Index: 8150446 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1420. Min Act: -0.1700
Data Index: 3068084 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1420. Min Act: -0.1700
Data Index: 2148504 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1263. Min Act: -0.1700
Data Index: 1220262 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1263. Min Act: -0.1700
Data Index: 1109717 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3777. Min Range: -3.3777
Max Act: 3.1263. Min Act: -0.1700
Data Index: 6316546 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19