Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3545 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1983. Min Range: -10.1983
Max Act: 10.1983. Min Act: -0.1700
Data Index: 4072685 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1983. Min Range: -10.1983
Max Act: 10.1358. Min Act: -0.1700
Data Index: 4390008 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1983. Min Range: -10.1983
Max Act: 10.0733. Min Act: -0.1700
Data Index: 5403625 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.8858. Min Act: -0.1700
Data Index: 6118361 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.5733. Min Act: -0.1700
Data Index: 1876104 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.5108. Min Act: -0.1700
Data Index: 4217472 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.3858. Min Act: -0.1700
Data Index: 6053445 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.2608. Min Act: -0.1700
Data Index: 5874581 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.1983. Min Act: -0.1700
Data Index: 2500759 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.1983. Min Act: -0.1700
Data Index: 5948926 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.1983. Min Act: -0.1700
Data Index: 1037398 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.1358. Min Act: -0.1700
Data Index: 276552 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.1358. Min Act: -0.1700
Data Index: 462188 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.1358. Min Act: -0.1700
Data Index: 5910353 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.1358. Min Act: -0.1700
Data Index: 1646636 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.1358. Min Act: -0.1700
Data Index: 5529721 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.1358. Min Act: -0.1700
Data Index: 4667992 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.0733. Min Act: -0.1700
Data Index: 4819766 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.0733. Min Act: -0.1700
Data Index: 4096737 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1983. Min Range: -10.1983
Max Act: 9.0108. Min Act: -0.1700
Data Index: 5555927 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19