Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4672 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.6614. Min Act: -0.1700
Data Index: 1089038 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.5364. Min Act: -0.1700
Data Index: 1607045 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.5052. Min Act: -0.1700
Data Index: 3514291 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.4114. Min Act: -0.1700
Data Index: 4200545 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.4114. Min Act: -0.1700
Data Index: 2257276 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.4114. Min Act: -0.1700
Data Index: 5487148 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.3802. Min Act: -0.1700
Data Index: 1529103 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.2864. Min Act: -0.1700
Data Index: 3692161 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.3177. Min Act: -0.1700
Data Index: 8363670 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.2864. Min Act: -0.1700
Data Index: 6221579 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.2864. Min Act: -0.1700
Data Index: 3370932 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.2864. Min Act: -0.1700
Data Index: 3683909 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.3177. Min Act: -0.1700
Data Index: 3692153 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.2864. Min Act: -0.1700
Data Index: 5068640 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.2864. Min Act: -0.1700
Data Index: 6126617 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.2239. Min Act: -0.1700
Data Index: 907847 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.2552. Min Act: -0.1700
Data Index: 2917033 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.2552. Min Act: -0.1700
Data Index: 2149942 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.2552. Min Act: -0.1700
Data Index: 1768308 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6614. Min Range: -5.6614
Max Act: 5.2239. Min Act: -0.1700
Data Index: 5011400 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19