Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3938 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6008. Min Range: -7.6008
Max Act: 7.6008. Min Act: -0.1700
Data Index: 5847294 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6008. Min Range: -7.6008
Max Act: 7.0383. Min Act: -0.1700
Data Index: 7953611 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.9758. Min Act: -0.1700
Data Index: 429899 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.9133. Min Act: -0.1700
Data Index: 6855016 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.9133. Min Act: -0.1700
Data Index: 1445684 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.8196. Min Act: -0.1700
Data Index: 6792716 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.8508. Min Act: -0.1700
Data Index: 5852626 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.8196. Min Act: -0.1700
Data Index: 3714577 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.7883. Min Act: -0.1700
Data Index: 4369148 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.7258. Min Act: -0.1700
Data Index: 4842035 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.7258. Min Act: -0.1700
Data Index: 708556 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.7258. Min Act: -0.1700
Data Index: 3818504 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.7258. Min Act: -0.1700
Data Index: 1603835 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.6946. Min Act: -0.1700
Data Index: 5816785 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.7258. Min Act: -0.1700
Data Index: 6776289 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.6946. Min Act: -0.1700
Data Index: 7513066 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.6321. Min Act: -0.1700
Data Index: 3285029 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.6321. Min Act: -0.1700
Data Index: 5504395 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.6321. Min Act: -0.1700
Data Index: 1268210 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6008. Min Range: -7.6008
Max Act: 6.6321. Min Act: -0.1700
Data Index: 6475717 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19