Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4062 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.3135. Min Act: -0.1700
Data Index: 7245537 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1885. Min Act: -0.1700
Data Index: 1893829 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1885. Min Act: -0.1700
Data Index: 1774757 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1573. Min Act: -0.1700
Data Index: 8377181 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1573. Min Act: -0.1700
Data Index: 896450 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1573. Min Act: -0.1700
Data Index: 376140 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1573. Min Act: -0.1700
Data Index: 3134305 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1573. Min Act: -0.1700
Data Index: 3914691 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1260. Min Act: -0.1700
Data Index: 8392022 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1260. Min Act: -0.1700
Data Index: 1820098 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1260. Min Act: -0.1700
Data Index: 5256317 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1260. Min Act: -0.1700
Data Index: 6466103 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1260. Min Act: -0.1700
Data Index: 2794986 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.0635. Min Act: -0.1700
Data Index: 7512866 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.0947. Min Act: -0.1700
Data Index: 770051 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.0947. Min Act: -0.1700
Data Index: 1221126 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1260. Min Act: -0.1700
Data Index: 6910493 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.1260. Min Act: -0.1700
Data Index: 5851224 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.0635. Min Act: -0.1700
Data Index: 132972 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3135. Min Range: -4.3135
Max Act: 4.0947. Min Act: -0.1700
Data Index: 3978252 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19