Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0622. Min Range: -7.0622
Max Act: 7.0622. Min Act: -0.1700
Data Index: 8053586 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.9685. Min Act: -0.1700
Data Index: 3535657 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.9060. Min Act: -0.1700
Data Index: 1709773 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.8747. Min Act: -0.1700
Data Index: 2466822 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.8435. Min Act: -0.1700
Data Index: 6242613 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.8122. Min Act: -0.1700
Data Index: 4388206 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.8122. Min Act: -0.1700
Data Index: 2575698 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.8122. Min Act: -0.1700
Data Index: 6698017 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.7810. Min Act: -0.1700
Data Index: 5171186 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.7497. Min Act: -0.1700
Data Index: 8579401 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.7810. Min Act: -0.1700
Data Index: 4926095 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.7810. Min Act: -0.1700
Data Index: 6411003 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.7497. Min Act: -0.1700
Data Index: 890660 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.7497. Min Act: -0.1700
Data Index: 3939 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.7497. Min Act: -0.1700
Data Index: 3643380 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.7497. Min Act: -0.1700
Data Index: 2387451 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.7497. Min Act: -0.1700
Data Index: 6993298 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.7810. Min Act: -0.1700
Data Index: 8407448 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.7497. Min Act: -0.1700
Data Index: 4440152 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0622. Min Range: -7.0622
Max Act: 6.7185. Min Act: -0.1700
Data Index: 1449084 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19