Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5608 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.8590. Min Act: -0.1700
Data Index: 8496054 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.6400. Min Act: -0.1700
Data Index: 3044143 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.5774. Min Act: -0.1700
Data Index: 2976162 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.5461. Min Act: -0.1700
Data Index: 4301655 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.5148. Min Act: -0.1700
Data Index: 6410529 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.5148. Min Act: -0.1700
Data Index: 3757946 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.4835. Min Act: -0.1700
Data Index: 7962949 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.5148. Min Act: -0.1700
Data Index: 7032791 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.5148. Min Act: -0.1700
Data Index: 7835838 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.5148. Min Act: -0.1700
Data Index: 4372800 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.4835. Min Act: -0.1700
Data Index: 6455316 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.4678. Min Act: -0.1700
Data Index: 4587283 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.4364. Min Act: -0.1700
Data Index: 5470983 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.4364. Min Act: -0.1700
Data Index: 2865032 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.4208. Min Act: -0.1700
Data Index: 5186210 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.4051. Min Act: -0.1700
Data Index: 1731300 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.4051. Min Act: -0.1700
Data Index: 7316931 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.4051. Min Act: -0.1700
Data Index: 2127576 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.4208. Min Act: -0.1700
Data Index: 775388 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8590. Min Range: -3.8590
Max Act: 3.3894. Min Act: -0.1700
Data Index: 6186440 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #19