Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3065 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.5804. Min Act: -0.1700
Data Index: 2952024 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.4866. Min Act: -0.1700
Data Index: 7077353 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.4554. Min Act: -0.1700
Data Index: 4240 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.3929. Min Act: -0.1700
Data Index: 3752152 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.3616. Min Act: -0.1700
Data Index: 6562757 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.3304. Min Act: -0.1700
Data Index: 5110468 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.3304. Min Act: -0.1700
Data Index: 8642840 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.3304. Min Act: -0.1700
Data Index: 6643131 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.2991. Min Act: -0.1700
Data Index: 4482377 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.2991. Min Act: -0.1700
Data Index: 171735 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.2679. Min Act: -0.1700
Data Index: 81120 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.2679. Min Act: -0.1700
Data Index: 5292491 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.2679. Min Act: -0.1700
Data Index: 3222973 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.2679. Min Act: -0.1700
Data Index: 3425924 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.2679. Min Act: -0.1700
Data Index: 8490103 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.2366. Min Act: -0.1700
Data Index: 6979488 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.2366. Min Act: -0.1700
Data Index: 4185158 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.2366. Min Act: -0.1700
Data Index: 120591 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.2366. Min Act: -0.1700
Data Index: 378186 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5804. Min Range: -6.5804
Max Act: 6.2366. Min Act: -0.1700
Data Index: 6071798 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #19