Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5087 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2955. Min Range: -5.2955
Max Act: 5.2955. Min Act: -0.1700
Data Index: 4080105 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2955. Min Range: -5.2955
Max Act: 5.2330. Min Act: -0.1700
Data Index: 6260087 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2955. Min Range: -5.2955
Max Act: 5.1705. Min Act: -0.1700
Data Index: 82083 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2955. Min Range: -5.2955
Max Act: 5.2018. Min Act: -0.1700
Data Index: 185246 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2955. Min Range: -5.2955
Max Act: 5.1080. Min Act: -0.1700
Data Index: 7458270 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2955. Min Range: -5.2955
Max Act: 5.1080. Min Act: -0.1700
Data Index: 403191 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2955. Min Range: -5.2955
Max Act: 5.0768. Min Act: -0.1700
Data Index: 2508534 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2955. Min Range: -5.2955
Max Act: 5.0768. Min Act: -0.1700
Data Index: 5627932 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2955. Min Range: -5.2955
Max Act: 5.0455. Min Act: -0.1700
Data Index: 3522908 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2955. Min Range: -5.2955
Max Act: 5.0143. Min Act: -0.1700
Data Index: 3781632 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2955. Min Range: -5.2955
Max Act: 5.0143. Min Act: -0.1700
Data Index: 2535410 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2955. Min Range: -5.2955
Max Act: 5.0143. Min Act: -0.1700
Data Index: 5696085 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2955. Min Range: -5.2955
Max Act: 4.9830. Min Act: -0.1700
Data Index: 6029375 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2955. Min Range: -5.2955
Max Act: 4.9830. Min Act: -0.1700
Data Index: 7570302 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2955. Min Range: -5.2955
Max Act: 4.9518. Min Act: -0.1700
Data Index: 1538196 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2955. Min Range: -5.2955
Max Act: 4.9518. Min Act: -0.1700
Data Index: 3328913 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2955. Min Range: -5.2955
Max Act: 4.9205. Min Act: -0.1700
Data Index: 2454149 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2955. Min Range: -5.2955
Max Act: 4.9205. Min Act: -0.1700
Data Index: 3602203 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2955. Min Range: -5.2955
Max Act: 4.9205. Min Act: -0.1700
Data Index: 7909771 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2955. Min Range: -5.2955
Max Act: 4.9205. Min Act: -0.1700
Data Index: 8474336 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #19