Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3143 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1478. Min Range: -4.1478
Max Act: 4.1478. Min Act: -0.1700
Data Index: 5435014 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1478. Min Range: -4.1478
Max Act: 4.0853. Min Act: -0.1700
Data Index: 4373546 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.9602. Min Act: -0.1700
Data Index: 122825 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.9290. Min Act: -0.1700
Data Index: 3848921 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.9133. Min Act: -0.1700
Data Index: 5815169 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.8977. Min Act: -0.1700
Data Index: 6355972 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.8508. Min Act: -0.1700
Data Index: 2088217 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.8352. Min Act: -0.1700
Data Index: 3021086 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.8508. Min Act: -0.1700
Data Index: 8631886 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.8352. Min Act: -0.1700
Data Index: 5755877 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.8039. Min Act: -0.1700
Data Index: 4519531 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.7570. Min Act: -0.1700
Data Index: 7040179 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.7570. Min Act: -0.1700
Data Index: 4598878 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.7570. Min Act: -0.1700
Data Index: 4392920 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.7413. Min Act: -0.1700
Data Index: 8366623 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.7257. Min Act: -0.1700
Data Index: 817534 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.7257. Min Act: -0.1700
Data Index: 6098342 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.6788. Min Act: -0.1700
Data Index: 5463656 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.6788. Min Act: -0.1700
Data Index: 8786011 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1478. Min Range: -4.1478
Max Act: 3.6631. Min Act: -0.1700
Data Index: 4129015 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19