Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1757 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1353. Min Range: -5.1353
Max Act: 5.1353. Min Act: -0.1700
Data Index: 1134943 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1353. Min Range: -5.1353
Max Act: 5.0728. Min Act: -0.1700
Data Index: 2904169 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1353. Min Range: -5.1353
Max Act: 5.0728. Min Act: -0.1700
Data Index: 891740 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.9166. Min Act: -0.1700
Data Index: 6616335 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.8541. Min Act: -0.1700
Data Index: 1053426 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.7916. Min Act: -0.1700
Data Index: 1903279 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.7916. Min Act: -0.1700
Data Index: 3379244 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.7603. Min Act: -0.1700
Data Index: 4682251 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.6978. Min Act: -0.1700
Data Index: 4865217 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.6978. Min Act: -0.1700
Data Index: 7953483 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.7291. Min Act: -0.1700
Data Index: 244418 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.6978. Min Act: -0.1700
Data Index: 5290193 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.7291. Min Act: -0.1700
Data Index: 6896724 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.6666. Min Act: -0.1700
Data Index: 7457379 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.6978. Min Act: -0.1700
Data Index: 5684763 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.6353. Min Act: -0.1700
Data Index: 5684210 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.6353. Min Act: -0.1700
Data Index: 1983683 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.6353. Min Act: -0.1700
Data Index: 1208421 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.6041. Min Act: -0.1700
Data Index: 5027100 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1353. Min Range: -5.1353
Max Act: 4.5728. Min Act: -0.1700
Data Index: 3603696 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #19