Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4798 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.7070. Min Act: -0.1700
Data Index: 8433808 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.7070. Min Act: -0.1700
Data Index: 7445634 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.6757. Min Act: -0.1700
Data Index: 4929041 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.6445. Min Act: -0.1700
Data Index: 4772413 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.6132. Min Act: -0.1700
Data Index: 4090571 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.6132. Min Act: -0.1700
Data Index: 7154854 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.6132. Min Act: -0.1700
Data Index: 5436120 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.5820. Min Act: -0.1700
Data Index: 231361 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.6132. Min Act: -0.1700
Data Index: 1267095 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.5507. Min Act: -0.1700
Data Index: 6008227 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.5507. Min Act: -0.1700
Data Index: 3842103 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.5507. Min Act: -0.1700
Data Index: 4325682 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.5507. Min Act: -0.1700
Data Index: 6482991 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.5507. Min Act: -0.1700
Data Index: 4825582 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.5507. Min Act: -0.1700
Data Index: 2187825 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.5195. Min Act: -0.1700
Data Index: 6163729 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.5195. Min Act: -0.1700
Data Index: 5151447 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.5195. Min Act: -0.1700
Data Index: 6388054 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.5195. Min Act: -0.1700
Data Index: 3252527 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7070. Min Range: -5.7070
Max Act: 5.4882. Min Act: -0.1700
Data Index: 2363797 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #19