Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4880 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.6966. Min Act: -0.1700
Data Index: 5400379 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5716. Min Act: -0.1700
Data Index: 3448052 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5404. Min Act: -0.1700
Data Index: 7649445 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.5091. Min Act: -0.1700
Data Index: 4558734 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.4779. Min Act: -0.1700
Data Index: 826969 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.4466. Min Act: -0.1700
Data Index: 3717956 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.4466. Min Act: -0.1700
Data Index: 7421167 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.4154. Min Act: -0.1700
Data Index: 530541 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.3841. Min Act: -0.1700
Data Index: 1694843 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.4154. Min Act: -0.1700
Data Index: 5617436 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.3841. Min Act: -0.1700
Data Index: 6605245 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.3841. Min Act: -0.1700
Data Index: 5662138 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.3529. Min Act: -0.1700
Data Index: 8125734 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.3841. Min Act: -0.1700
Data Index: 3409017 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.3841. Min Act: -0.1700
Data Index: 5729557 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.3529. Min Act: -0.1700
Data Index: 8101666 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.3529. Min Act: -0.1700
Data Index: 3400167 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.3216. Min Act: -0.1700
Data Index: 5400380 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.2904. Min Act: -0.1700
Data Index: 442195 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6966. Min Range: -5.6966
Max Act: 5.3216. Min Act: -0.1700
Data Index: 3035120 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19