Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1907 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.5008. Min Act: -0.1700
Data Index: 5064953 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.3758. Min Act: -0.1700
Data Index: 4101938 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.2508. Min Act: -0.1700
Data Index: 8663614 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.2195. Min Act: -0.1700
Data Index: 6859818 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.2195. Min Act: -0.1700
Data Index: 7048187 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.2195. Min Act: -0.1700
Data Index: 4923809 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.2195. Min Act: -0.1700
Data Index: 5396575 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.2195. Min Act: -0.1700
Data Index: 5434600 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.2195. Min Act: -0.1700
Data Index: 604192 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.1882. Min Act: -0.1700
Data Index: 5355031 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.1882. Min Act: -0.1700
Data Index: 7668113 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.1570. Min Act: -0.1700
Data Index: 5453391 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.1882. Min Act: -0.1700
Data Index: 398672 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.1882. Min Act: -0.1700
Data Index: 4554354 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.1570. Min Act: -0.1700
Data Index: 731360 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.1257. Min Act: -0.1700
Data Index: 4734080 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.0945. Min Act: -0.1700
Data Index: 519444 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.0632. Min Act: -0.1700
Data Index: 1272857 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.0945. Min Act: -0.1700
Data Index: 4037089 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5008. Min Range: -4.5008
Max Act: 4.0945. Min Act: -0.1700
Data Index: 2171722 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #19