Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5405 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0183. Min Range: -7.0183
Max Act: 7.0183. Min Act: -0.1700
Data Index: 7751619 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.8933. Min Act: -0.1700
Data Index: 7751601 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.8933. Min Act: -0.1700
Data Index: 7797711 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7996. Min Act: -0.1700
Data Index: 6315298 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7996. Min Act: -0.1700
Data Index: 5902146 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7996. Min Act: -0.1700
Data Index: 4980218 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7683. Min Act: -0.1700
Data Index: 987508 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7683. Min Act: -0.1700
Data Index: 7751604 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7683. Min Act: -0.1700
Data Index: 7751600 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7683. Min Act: -0.1700
Data Index: 7751614 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7371. Min Act: -0.1700
Data Index: 7751599 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7371. Min Act: -0.1700
Data Index: 3204653 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7371. Min Act: -0.1700
Data Index: 7751620 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7058. Min Act: -0.1700
Data Index: 7228107 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7058. Min Act: -0.1700
Data Index: 7751609 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7058. Min Act: -0.1700
Data Index: 7751617 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7058. Min Act: -0.1700
Data Index: 7798423 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7058. Min Act: -0.1700
Data Index: 3864816 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7058. Min Act: -0.1700
Data Index: 2909 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0183. Min Range: -7.0183
Max Act: 6.7058. Min Act: -0.1700
Data Index: 5009601 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19