Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4811 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.5160. Min Act: -0.1700
Data Index: 6821844 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.4836. Min Act: -0.1700
Data Index: 1280498 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.3860. Min Act: -0.1700
Data Index: 2012609 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.3860. Min Act: -0.1700
Data Index: 8230902 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.3860. Min Act: -0.1700
Data Index: 1942967 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.3369. Min Act: -0.1700
Data Index: 1356965 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.3369. Min Act: -0.1700
Data Index: 1467754 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.3369. Min Act: -0.1700
Data Index: 4034021 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.3369. Min Act: -0.1700
Data Index: 4600229 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.3369. Min Act: -0.1700
Data Index: 52251 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.3040. Min Act: -0.1700
Data Index: 5053516 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.3204. Min Act: -0.1700
Data Index: 242686 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.3040. Min Act: -0.1700
Data Index: 3532497 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.2876. Min Act: -0.1700
Data Index: 3500583 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.2876. Min Act: -0.1700
Data Index: 5092811 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.2711. Min Act: -0.1700
Data Index: 6515170 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.2876. Min Act: -0.1700
Data Index: 159097 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.2711. Min Act: -0.1700
Data Index: 2403174 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.2876. Min Act: -0.1700
Data Index: 4671737 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5160. Min Range: -2.5160
Max Act: 2.2711. Min Act: -0.1700
Data Index: 6511819 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19