Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 954 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.3938. Min Act: -0.1700
Data Index: 4464080 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.3626. Min Act: -0.1700
Data Index: 1849047 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.3313. Min Act: -0.1700
Data Index: 4521660 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.3001. Min Act: -0.1700
Data Index: 4424383 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.3001. Min Act: -0.1700
Data Index: 6762332 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.2376. Min Act: -0.1700
Data Index: 6512075 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.2376. Min Act: -0.1700
Data Index: 5075253 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.2063. Min Act: -0.1700
Data Index: 8063387 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.2063. Min Act: -0.1700
Data Index: 2081629 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.2063. Min Act: -0.1700
Data Index: 5702113 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.2063. Min Act: -0.1700
Data Index: 1419690 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.1438. Min Act: -0.1700
Data Index: 6965718 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.1751. Min Act: -0.1700
Data Index: 1160934 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.1438. Min Act: -0.1700
Data Index: 7560253 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.1438. Min Act: -0.1700
Data Index: 1286702 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.1126. Min Act: -0.1700
Data Index: 4812858 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.1438. Min Act: -0.1700
Data Index: 1957308 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.1126. Min Act: -0.1700
Data Index: 206804 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.1126. Min Act: -0.1700
Data Index: 4397156 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3938. Min Range: -5.3938
Max Act: 5.1438. Min Act: -0.1700
Data Index: 2999490 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19