Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2092 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1632. Min Range: -6.1632
Max Act: 6.1632. Min Act: -0.1700
Data Index: 821116 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1632. Min Range: -6.1632
Max Act: 6.0694. Min Act: -0.1700
Data Index: 4998347 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.9757. Min Act: -0.1700
Data Index: 4759719 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.9757. Min Act: -0.1700
Data Index: 1877558 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.8819. Min Act: -0.1700
Data Index: 2588283 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.8507. Min Act: -0.1700
Data Index: 6531606 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.8819. Min Act: -0.1700
Data Index: 7112470 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.8194. Min Act: -0.1700
Data Index: 6880569 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.8194. Min Act: -0.1700
Data Index: 7787162 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.7882. Min Act: -0.1700
Data Index: 768924 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.7882. Min Act: -0.1700
Data Index: 387710 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.7257. Min Act: -0.1700
Data Index: 8399101 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.7257. Min Act: -0.1700
Data Index: 6531847 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.7257. Min Act: -0.1700
Data Index: 6863922 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.6944. Min Act: -0.1700
Data Index: 1009083 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.6944. Min Act: -0.1700
Data Index: 885934 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.6944. Min Act: -0.1700
Data Index: 2717480 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.6632. Min Act: -0.1700
Data Index: 2471765 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.6632. Min Act: -0.1700
Data Index: 1137765 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1632. Min Range: -6.1632
Max Act: 5.6632. Min Act: -0.1700
Data Index: 7138814 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #19