Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5887 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1491. Min Range: -4.1491
Max Act: 4.1491. Min Act: -0.1700
Data Index: 7446471 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.8990. Min Act: -0.1700
Data Index: 4776023 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.7896. Min Act: -0.1700
Data Index: 6936862 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.7583. Min Act: -0.1700
Data Index: 4376486 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.7427. Min Act: -0.1700
Data Index: 3592355 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.7427. Min Act: -0.1700
Data Index: 162950 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.7114. Min Act: -0.1700
Data Index: 8812357 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.7114. Min Act: -0.1700
Data Index: 7350786 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.7114. Min Act: -0.1700
Data Index: 3502159 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.6645. Min Act: -0.1700
Data Index: 6314087 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.6801. Min Act: -0.1700
Data Index: 8023620 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.6332. Min Act: -0.1700
Data Index: 2212333 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.6175. Min Act: -0.1700
Data Index: 2414530 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.6175. Min Act: -0.1700
Data Index: 1175128 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.6019. Min Act: -0.1700
Data Index: 3211057 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.6019. Min Act: -0.1700
Data Index: 5652515 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.6019. Min Act: -0.1700
Data Index: 226792 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.5862. Min Act: -0.1700
Data Index: 8229210 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.5549. Min Act: -0.1700
Data Index: 1021263 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1491. Min Range: -4.1491
Max Act: 3.5549. Min Act: -0.1700
Data Index: 1693035 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19