Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4099 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.9987. Min Act: -0.1700
Data Index: 7923427 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.9675. Min Act: -0.1700
Data Index: 652971 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.8425. Min Act: -0.1700
Data Index: 2153577 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.7800. Min Act: -0.1700
Data Index: 2900729 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.8112. Min Act: -0.1700
Data Index: 2937424 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.7800. Min Act: -0.1700
Data Index: 8042124 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.7487. Min Act: -0.1700
Data Index: 2432392 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.7175. Min Act: -0.1700
Data Index: 6948858 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.7175. Min Act: -0.1700
Data Index: 1517511 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.6862. Min Act: -0.1700
Data Index: 6948857 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.6237. Min Act: -0.1700
Data Index: 6452460 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.6237. Min Act: -0.1700
Data Index: 8340787 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.5612. Min Act: -0.1700
Data Index: 4513272 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.6237. Min Act: -0.1700
Data Index: 3350903 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.5300. Min Act: -0.1700
Data Index: 1193150 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.5300. Min Act: -0.1700
Data Index: 5028595 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.4987. Min Act: -0.1700
Data Index: 8691188 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.5300. Min Act: -0.1700
Data Index: 8779327 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.5300. Min Act: -0.1700
Data Index: 6009397 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9987. Min Range: -6.9987
Max Act: 6.5300. Min Act: -0.1700
Data Index: 6198967 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19