Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1426 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.7244. Min Act: -0.1700
Data Index: 8208686 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.6932. Min Act: -0.1700
Data Index: 5094584 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.6307. Min Act: -0.1700
Data Index: 6085184 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.5994. Min Act: -0.1700
Data Index: 6664114 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.4432. Min Act: -0.1700
Data Index: 1759602 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.4432. Min Act: -0.1700
Data Index: 2042137 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.4432. Min Act: -0.1700
Data Index: 7227303 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.4119. Min Act: -0.1700
Data Index: 3080812 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.4119. Min Act: -0.1700
Data Index: 1181433 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.4432. Min Act: -0.1700
Data Index: 5689528 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.4119. Min Act: -0.1700
Data Index: 74989 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.4119. Min Act: -0.1700
Data Index: 4618494 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.3807. Min Act: -0.1700
Data Index: 8181096 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.3807. Min Act: -0.1700
Data Index: 8677111 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.3494. Min Act: -0.1700
Data Index: 7123229 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.3494. Min Act: -0.1700
Data Index: 1692023 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.3494. Min Act: -0.1700
Data Index: 5149017 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.3494. Min Act: -0.1700
Data Index: 758524 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.3182. Min Act: -0.1700
Data Index: 7137047 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7244. Min Range: -4.7244
Max Act: 4.3182. Min Act: -0.1700
Data Index: 7539832 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19