Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1823 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1183. Min Range: -6.1183
Max Act: 6.1183. Min Act: -0.1700
Data Index: 4093605 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1183. Min Range: -6.1183
Max Act: 6.0871. Min Act: -0.1700
Data Index: 1216989 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1183. Min Range: -6.1183
Max Act: 6.0558. Min Act: -0.1700
Data Index: 2792144 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1183. Min Range: -6.1183
Max Act: 6.0246. Min Act: -0.1700
Data Index: 3002573 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1183. Min Range: -6.1183
Max Act: 6.0871. Min Act: -0.1700
Data Index: 2338249 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1183. Min Range: -6.1183
Max Act: 6.0871. Min Act: -0.1700
Data Index: 6297525 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1183. Min Range: -6.1183
Max Act: 6.0246. Min Act: -0.1700
Data Index: 8447027 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1183. Min Range: -6.1183
Max Act: 6.0246. Min Act: -0.1700
Data Index: 2417862 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1183. Min Range: -6.1183
Max Act: 6.0246. Min Act: -0.1700
Data Index: 5817472 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1183. Min Range: -6.1183
Max Act: 5.9933. Min Act: -0.1700
Data Index: 7610608 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1183. Min Range: -6.1183
Max Act: 5.9933. Min Act: -0.1700
Data Index: 8385755 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1183. Min Range: -6.1183
Max Act: 5.9621. Min Act: -0.1700
Data Index: 6368572 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1183. Min Range: -6.1183
Max Act: 5.9621. Min Act: -0.1700
Data Index: 1166338 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1183. Min Range: -6.1183
Max Act: 5.9308. Min Act: -0.1700
Data Index: 6398890 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1183. Min Range: -6.1183
Max Act: 5.9308. Min Act: -0.1700
Data Index: 4814294 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1183. Min Range: -6.1183
Max Act: 5.9308. Min Act: -0.1700
Data Index: 1432651 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1183. Min Range: -6.1183
Max Act: 5.9308. Min Act: -0.1700
Data Index: 2338250 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1183. Min Range: -6.1183
Max Act: 5.8996. Min Act: -0.1700
Data Index: 67351 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1183. Min Range: -6.1183
Max Act: 5.9308. Min Act: -0.1700
Data Index: 1969032 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1183. Min Range: -6.1183
Max Act: 5.8996. Min Act: -0.1700
Data Index: 5556670 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19