Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 544 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9624. Min Range: -8.9624
Max Act: 8.9624. Min Act: -0.1700
Data Index: 4710921 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9624. Min Range: -8.9624
Max Act: 8.2124. Min Act: -0.1700
Data Index: 4119523 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9624. Min Range: -8.9624
Max Act: 8.1499. Min Act: -0.1700
Data Index: 3424800 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9624. Min Range: -8.9624
Max Act: 8.0874. Min Act: -0.1700
Data Index: 3475037 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.9936. Min Act: -0.1700
Data Index: 2184969 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.9624. Min Act: -0.1700
Data Index: 1044598 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.9936. Min Act: -0.1700
Data Index: 8365148 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.9624. Min Act: -0.1700
Data Index: 5144555 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.9624. Min Act: -0.1700
Data Index: 7269387 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.8999. Min Act: -0.1700
Data Index: 3133349 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.8999. Min Act: -0.1700
Data Index: 872289 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.8686. Min Act: -0.1700
Data Index: 8731018 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.8374. Min Act: -0.1700
Data Index: 7962477 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.8686. Min Act: -0.1700
Data Index: 2189674 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.8061. Min Act: -0.1700
Data Index: 7241910 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.8374. Min Act: -0.1700
Data Index: 6360876 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.7749. Min Act: -0.1700
Data Index: 3560385 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.7124. Min Act: -0.1700
Data Index: 4248937 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.7124. Min Act: -0.1700
Data Index: 6080247 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9624. Min Range: -8.9624
Max Act: 7.6499. Min Act: -0.1700
Data Index: 3036022 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19