Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5642 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.6818. Min Act: -0.1700
Data Index: 6548943 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.4006. Min Act: -0.1700
Data Index: 5955559 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.3693. Min Act: -0.1700
Data Index: 7923655 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.3693. Min Act: -0.1700
Data Index: 289353 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.3693. Min Act: -0.1700
Data Index: 1855638 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.3381. Min Act: -0.1700
Data Index: 5823395 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.3381. Min Act: -0.1700
Data Index: 1222491 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.3693. Min Act: -0.1700
Data Index: 8266828 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.3381. Min Act: -0.1700
Data Index: 4014420 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.3381. Min Act: -0.1700
Data Index: 2731545 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.3068. Min Act: -0.1700
Data Index: 1980939 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.3068. Min Act: -0.1700
Data Index: 6683974 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.3068. Min Act: -0.1700
Data Index: 6046472 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.3068. Min Act: -0.1700
Data Index: 5927588 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.2755. Min Act: -0.1700
Data Index: 2679727 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.2755. Min Act: -0.1700
Data Index: 5823393 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.2755. Min Act: -0.1700
Data Index: 44137 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.2443. Min Act: -0.1700
Data Index: 4490337 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.2755. Min Act: -0.1700
Data Index: 986735 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6818. Min Range: -4.6818
Max Act: 4.2443. Min Act: -0.1700
Data Index: 5750330 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19