Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4083 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.6030. Min Act: -0.1700
Data Index: 2407608 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.5092. Min Act: -0.1700
Data Index: 7603433 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.5092. Min Act: -0.1700
Data Index: 2533311 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.5092. Min Act: -0.1700
Data Index: 1443729 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.4155. Min Act: -0.1700
Data Index: 2987775 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.4467. Min Act: -0.1700
Data Index: 1155042 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.4155. Min Act: -0.1700
Data Index: 4385460 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.3842. Min Act: -0.1700
Data Index: 5450767 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.3842. Min Act: -0.1700
Data Index: 2294649 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.3842. Min Act: -0.1700
Data Index: 8698767 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.3842. Min Act: -0.1700
Data Index: 2152040 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.3530. Min Act: -0.1700
Data Index: 4596834 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.3217. Min Act: -0.1700
Data Index: 7570683 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.3530. Min Act: -0.1700
Data Index: 5401839 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.3217. Min Act: -0.1700
Data Index: 4471508 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.3217. Min Act: -0.1700
Data Index: 5421296 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.3217. Min Act: -0.1700
Data Index: 894099 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.2905. Min Act: -0.1700
Data Index: 3556806 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.2905. Min Act: -0.1700
Data Index: 2597781 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6030. Min Range: -5.6030
Max Act: 5.2905. Min Act: -0.1700
Data Index: 600110 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19