Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2726 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2636. Min Range: -7.2636
Max Act: 7.2636. Min Act: -0.1700
Data Index: 6211076 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2636. Min Range: -7.2636
Max Act: 7.2636. Min Act: -0.1700
Data Index: 6211068 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2636. Min Range: -7.2636
Max Act: 7.1386. Min Act: -0.1700
Data Index: 6211065 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.7011. Min Act: -0.1700
Data Index: 7872177 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.7323. Min Act: -0.1700
Data Index: 5906057 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.6386. Min Act: -0.1700
Data Index: 6211073 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.6073. Min Act: -0.1700
Data Index: 984020 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.5136. Min Act: -0.1700
Data Index: 1592688 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.5136. Min Act: -0.1700
Data Index: 6931038 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.4511. Min Act: -0.1700
Data Index: 6878310 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.4823. Min Act: -0.1700
Data Index: 6211074 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.4823. Min Act: -0.1700
Data Index: 3265324 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.4823. Min Act: -0.1700
Data Index: 6213145 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.4198. Min Act: -0.1700
Data Index: 5530700 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.4511. Min Act: -0.1700
Data Index: 6211066 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.4511. Min Act: -0.1700
Data Index: 7525889 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.4511. Min Act: -0.1700
Data Index: 905564 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.3886. Min Act: -0.1700
Data Index: 4409471 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.3886. Min Act: -0.1700
Data Index: 356905 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2636. Min Range: -7.2636
Max Act: 6.3886. Min Act: -0.1700
Data Index: 4135926 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19