Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5118 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.3047. Min Act: -0.1700
Data Index: 2993653 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.2262. Min Act: -0.1700
Data Index: 7743977 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1790. Min Act: -0.1700
Data Index: 8210397 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1632. Min Act: -0.1700
Data Index: 8568777 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1790. Min Act: -0.1700
Data Index: 7761144 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1318. Min Act: -0.1700
Data Index: 2620118 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1475. Min Act: -0.1700
Data Index: 5519624 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1475. Min Act: -0.1700
Data Index: 1412751 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1160. Min Act: -0.1700
Data Index: 1427853 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.1160. Min Act: -0.1700
Data Index: 8106644 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.0687. Min Act: -0.1700
Data Index: 6355058 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.0845. Min Act: -0.1700
Data Index: 3799382 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.0372. Min Act: -0.1700
Data Index: 6376839 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.0529. Min Act: -0.1700
Data Index: 5124734 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.0372. Min Act: -0.1700
Data Index: 6976273 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.0529. Min Act: -0.1700
Data Index: 5221384 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.0529. Min Act: -0.1700
Data Index: 3653011 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.0214. Min Act: -0.1700
Data Index: 7416337 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.0372. Min Act: -0.1700
Data Index: 3111887 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3047. Min Range: -3.3047
Max Act: 3.0372. Min Act: -0.1700
Data Index: 1867914 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #19