Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4122 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.9772. Min Act: -0.1700
Data Index: 5709517 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.7897. Min Act: -0.1700
Data Index: 7028632 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.7897. Min Act: -0.1700
Data Index: 3717230 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.8522. Min Act: -0.1700
Data Index: 7594157 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.6022. Min Act: -0.1700
Data Index: 6288248 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.4772. Min Act: -0.1700
Data Index: 6625074 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.4772. Min Act: -0.1700
Data Index: 1960052 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.4147. Min Act: -0.1700
Data Index: 3888311 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.4147. Min Act: -0.1700
Data Index: 4487598 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.3522. Min Act: -0.1700
Data Index: 3659762 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.3522. Min Act: -0.1700
Data Index: 7329012 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.2897. Min Act: -0.1700
Data Index: 669685 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.2897. Min Act: -0.1700
Data Index: 3315562 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.2897. Min Act: -0.1700
Data Index: 937021 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.1647. Min Act: -0.1700
Data Index: 8602495 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.1647. Min Act: -0.1700
Data Index: 4845454 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.1647. Min Act: -0.1700
Data Index: 7354513 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.1022. Min Act: -0.1700
Data Index: 4312214 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.1022. Min Act: -0.1700
Data Index: 477665 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9772. Min Range: -8.9772
Max Act: 8.1022. Min Act: -0.1700
Data Index: 2483270 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19