Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.5806. Min Act: -0.1700
Data Index: 4265637 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.5494. Min Act: -0.1700
Data Index: 5159352 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.5181. Min Act: -0.1700
Data Index: 5159354 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.3931. Min Act: -0.1700
Data Index: 7313076 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.3306. Min Act: -0.1700
Data Index: 3948927 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.3306. Min Act: -0.1700
Data Index: 7392496 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.2369. Min Act: -0.1700
Data Index: 7656152 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.2681. Min Act: -0.1700
Data Index: 8208380 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.2056. Min Act: -0.1700
Data Index: 6613703 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.1744. Min Act: -0.1700
Data Index: 2098978 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.1744. Min Act: -0.1700
Data Index: 179803 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.1744. Min Act: -0.1700
Data Index: 235680 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.1431. Min Act: -0.1700
Data Index: 7656151 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.1431. Min Act: -0.1700
Data Index: 781277 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.1431. Min Act: -0.1700
Data Index: 2149296 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.1431. Min Act: -0.1700
Data Index: 5684575 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.1119. Min Act: -0.1700
Data Index: 6914795 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.1119. Min Act: -0.1700
Data Index: 7876655 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.1119. Min Act: -0.1700
Data Index: 1557661 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5806. Min Range: -5.5806
Max Act: 5.0806. Min Act: -0.1700
Data Index: 125591 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #19