Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4514 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.7558. Min Act: -0.1700
Data Index: 1809632 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.6933. Min Act: -0.1700
Data Index: 1809622 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.6621. Min Act: -0.1700
Data Index: 3994924 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.6621. Min Act: -0.1700
Data Index: 93219 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.6308. Min Act: -0.1700
Data Index: 7266562 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.6308. Min Act: -0.1700
Data Index: 2514934 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.6308. Min Act: -0.1700
Data Index: 2964666 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.5996. Min Act: -0.1700
Data Index: 833004 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.5683. Min Act: -0.1700
Data Index: 1610568 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.5371. Min Act: -0.1700
Data Index: 8193513 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.5371. Min Act: -0.1700
Data Index: 977556 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.5683. Min Act: -0.1700
Data Index: 7517448 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.5371. Min Act: -0.1700
Data Index: 3363538 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.5371. Min Act: -0.1700
Data Index: 1809629 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.5058. Min Act: -0.1700
Data Index: 6821796 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.5058. Min Act: -0.1700
Data Index: 5189986 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.5058. Min Act: -0.1700
Data Index: 1243926 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.4746. Min Act: -0.1700
Data Index: 7644112 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.5058. Min Act: -0.1700
Data Index: 6067436 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7558. Min Range: -6.7558
Max Act: 6.4746. Min Act: -0.1700
Data Index: 4796655 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19