Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5567 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3762. Min Range: -5.3762
Max Act: 5.3762. Min Act: -0.1700
Data Index: 4978738 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3762. Min Range: -5.3762
Max Act: 5.2199. Min Act: -0.1700
Data Index: 395328 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3762. Min Range: -5.3762
Max Act: 5.0949. Min Act: -0.1700
Data Index: 1127615 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3762. Min Range: -5.3762
Max Act: 5.0949. Min Act: -0.1700
Data Index: 6393374 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3762. Min Range: -5.3762
Max Act: 5.0949. Min Act: -0.1700
Data Index: 3815262 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3762. Min Range: -5.3762
Max Act: 5.0324. Min Act: -0.1700
Data Index: 6853706 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3762. Min Range: -5.3762
Max Act: 5.0012. Min Act: -0.1700
Data Index: 4100048 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.9387. Min Act: -0.1700
Data Index: 3974107 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.9387. Min Act: -0.1700
Data Index: 5510112 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.9074. Min Act: -0.1700
Data Index: 686826 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.9074. Min Act: -0.1700
Data Index: 6969678 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.9074. Min Act: -0.1700
Data Index: 8558053 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.8762. Min Act: -0.1700
Data Index: 3436626 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.8449. Min Act: -0.1700
Data Index: 3053817 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.8449. Min Act: -0.1700
Data Index: 974509 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.8449. Min Act: -0.1700
Data Index: 272051 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.8137. Min Act: -0.1700
Data Index: 5126464 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.8137. Min Act: -0.1700
Data Index: 819116 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.7824. Min Act: -0.1700
Data Index: 1747172 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3762. Min Range: -5.3762
Max Act: 4.7824. Min Act: -0.1700
Data Index: 1251100 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #19