Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3030. Min Range: -8.3030
Max Act: 8.3030. Min Act: -0.1700
Data Index: 2277630 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3030. Min Range: -8.3030
Max Act: 7.8655. Min Act: -0.1700
Data Index: 2847738 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3030. Min Range: -8.3030
Max Act: 7.7717. Min Act: -0.1700
Data Index: 2882445 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3030. Min Range: -8.3030
Max Act: 7.6155. Min Act: -0.1700
Data Index: 6848773 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3030. Min Range: -8.3030
Max Act: 7.4905. Min Act: -0.1700
Data Index: 4644766 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3030. Min Range: -8.3030
Max Act: 7.3967. Min Act: -0.1700
Data Index: 372866 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3030. Min Range: -8.3030
Max Act: 7.3342. Min Act: -0.1700
Data Index: 3197838 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3030. Min Range: -8.3030
Max Act: 7.1155. Min Act: -0.1700
Data Index: 1874298 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3030. Min Range: -8.3030
Max Act: 7.0842. Min Act: -0.1700
Data Index: 1810911 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3030. Min Range: -8.3030
Max Act: 7.0530. Min Act: -0.1700
Data Index: 6652588 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3030. Min Range: -8.3030
Max Act: 7.0217. Min Act: -0.1700
Data Index: 480019 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3030. Min Range: -8.3030
Max Act: 7.0217. Min Act: -0.1700
Data Index: 5978972 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3030. Min Range: -8.3030
Max Act: 6.9592. Min Act: -0.1700
Data Index: 2564062 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3030. Min Range: -8.3030
Max Act: 6.9280. Min Act: -0.1700
Data Index: 7859272 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3030. Min Range: -8.3030
Max Act: 6.9280. Min Act: -0.1700
Data Index: 5745650 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3030. Min Range: -8.3030
Max Act: 6.9280. Min Act: -0.1700
Data Index: 6955278 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3030. Min Range: -8.3030
Max Act: 6.8967. Min Act: -0.1700
Data Index: 3002329 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3030. Min Range: -8.3030
Max Act: 6.8655. Min Act: -0.1700
Data Index: 3270955 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3030. Min Range: -8.3030
Max Act: 6.8342. Min Act: -0.1700
Data Index: 372873 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3030. Min Range: -8.3030
Max Act: 6.8655. Min Act: -0.1700
Data Index: 4799078 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19