Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.9100. Min Act: -0.1700
Data Index: 4547895 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.7538. Min Act: -0.1700
Data Index: 1388593 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.7225. Min Act: -0.1700
Data Index: 26246 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.7225. Min Act: -0.1700
Data Index: 1390446 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.7225. Min Act: -0.1700
Data Index: 7841545 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6600. Min Act: -0.1700
Data Index: 4953271 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6913. Min Act: -0.1700
Data Index: 7887022 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.7225. Min Act: -0.1700
Data Index: 5326746 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6913. Min Act: -0.1700
Data Index: 6561354 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6600. Min Act: -0.1700
Data Index: 3835244 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6600. Min Act: -0.1700
Data Index: 8490123 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6600. Min Act: -0.1700
Data Index: 3431892 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6288. Min Act: -0.1700
Data Index: 3187265 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6288. Min Act: -0.1700
Data Index: 5546396 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6288. Min Act: -0.1700
Data Index: 7283360 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6288. Min Act: -0.1700
Data Index: 7270031 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.5975. Min Act: -0.1700
Data Index: 3220334 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.5975. Min Act: -0.1700
Data Index: 4130491 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.6288. Min Act: -0.1700
Data Index: 5150512 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9100. Min Range: -4.9100
Max Act: 4.5975. Min Act: -0.1700
Data Index: 4843896 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19