Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4134 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.6962. Min Act: -0.1700
Data Index: 1549265 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.6962. Min Act: -0.1700
Data Index: 6296524 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.6962. Min Act: -0.1700
Data Index: 685257 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.6650. Min Act: -0.1700
Data Index: 4355607 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.6025. Min Act: -0.1700
Data Index: 2004923 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.6025. Min Act: -0.1700
Data Index: 6627926 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.5400. Min Act: -0.1700
Data Index: 873052 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.4775. Min Act: -0.1700
Data Index: 4762399 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.4150. Min Act: -0.1700
Data Index: 1162486 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.4462. Min Act: -0.1700
Data Index: 5973942 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.4462. Min Act: -0.1700
Data Index: 3699506 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.4462. Min Act: -0.1700
Data Index: 6617691 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.4775. Min Act: -0.1700
Data Index: 5274366 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.3837. Min Act: -0.1700
Data Index: 7919811 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.3837. Min Act: -0.1700
Data Index: 6584385 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.3837. Min Act: -0.1700
Data Index: 6403903 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.3837. Min Act: -0.1700
Data Index: 7814221 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.3525. Min Act: -0.1700
Data Index: 16933 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.3837. Min Act: -0.1700
Data Index: 26652 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6962. Min Range: -5.6962
Max Act: 5.3525. Min Act: -0.1700
Data Index: 6758822 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19