Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2630 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1512. Min Range: -7.1512
Max Act: 7.1512. Min Act: -0.1700
Data Index: 6726787 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.5262. Min Act: -0.1700
Data Index: 4408 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.3075. Min Act: -0.1700
Data Index: 5895701 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.2762. Min Act: -0.1700
Data Index: 3067180 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.2450. Min Act: -0.1700
Data Index: 577074 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.2450. Min Act: -0.1700
Data Index: 7377749 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.2450. Min Act: -0.1700
Data Index: 4520130 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.2137. Min Act: -0.1700
Data Index: 1192336 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.2137. Min Act: -0.1700
Data Index: 8060370 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.1825. Min Act: -0.1700
Data Index: 5297372 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.1512. Min Act: -0.1700
Data Index: 3822920 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.1512. Min Act: -0.1700
Data Index: 2583094 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.0887. Min Act: -0.1700
Data Index: 4373013 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.0887. Min Act: -0.1700
Data Index: 4174704 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.0887. Min Act: -0.1700
Data Index: 6711254 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.0887. Min Act: -0.1700
Data Index: 1095740 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.0887. Min Act: -0.1700
Data Index: 7377742 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.0262. Min Act: -0.1700
Data Index: 5490699 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1512. Min Range: -7.1512
Max Act: 6.0262. Min Act: -0.1700
Data Index: 2074615 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1512. Min Range: -7.1512
Max Act: 5.9950. Min Act: -0.1700
Data Index: 5343182 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19