Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4320 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0735. Min Range: -5.0735
Max Act: 5.0735. Min Act: -0.1700
Data Index: 1248262 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.9172. Min Act: -0.1700
Data Index: 4330068 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.9172. Min Act: -0.1700
Data Index: 8358337 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.8860. Min Act: -0.1700
Data Index: 5353301 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.8235. Min Act: -0.1700
Data Index: 4591118 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.7922. Min Act: -0.1700
Data Index: 5853749 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.8235. Min Act: -0.1700
Data Index: 6979319 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.7297. Min Act: -0.1700
Data Index: 173713 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.7610. Min Act: -0.1700
Data Index: 4620949 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.7610. Min Act: -0.1700
Data Index: 5156973 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.7297. Min Act: -0.1700
Data Index: 4473548 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.7297. Min Act: -0.1700
Data Index: 1200306 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.7297. Min Act: -0.1700
Data Index: 6230751 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.6985. Min Act: -0.1700
Data Index: 491976 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.6985. Min Act: -0.1697
Data Index: 2098798 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.6672. Min Act: -0.1700
Data Index: 3061172 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.6672. Min Act: -0.1700
Data Index: 2191958 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.6672. Min Act: -0.1700
Data Index: 7352839 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.6672. Min Act: -0.1700
Data Index: 877624 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0735. Min Range: -5.0735
Max Act: 4.6672. Min Act: -0.1700
Data Index: 6291504 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #19