Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3325 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.8450. Min Act: -0.1700
Data Index: 538766 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.7825. Min Act: -0.1700
Data Index: 2616527 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.7825. Min Act: -0.1700
Data Index: 2380357 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.6887. Min Act: -0.1700
Data Index: 1414660 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.6262. Min Act: -0.1700
Data Index: 1403689 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.6575. Min Act: -0.1700
Data Index: 2955446 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.6262. Min Act: -0.1700
Data Index: 1593766 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.6262. Min Act: -0.1700
Data Index: 350011 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.5950. Min Act: -0.1700
Data Index: 6230275 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.5637. Min Act: -0.1700
Data Index: 6400622 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.5325. Min Act: -0.1700
Data Index: 4395428 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.5325. Min Act: -0.1700
Data Index: 6907479 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.5325. Min Act: -0.1700
Data Index: 2078634 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.5012. Min Act: -0.1700
Data Index: 2871674 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.4700. Min Act: -0.1700
Data Index: 8368368 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.5325. Min Act: -0.1700
Data Index: 8023689 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.4075. Min Act: -0.1700
Data Index: 5543157 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.4075. Min Act: -0.1700
Data Index: 1514175 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.4075. Min Act: -0.1700
Data Index: 7456655 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8450. Min Range: -6.8450
Max Act: 6.4075. Min Act: -0.1700
Data Index: 7570609 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19