Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2991 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.5725. Min Act: -0.1700
Data Index: 8272112 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.5413. Min Act: -0.1700
Data Index: 531159 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.5100. Min Act: -0.1700
Data Index: 2064958 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.5100. Min Act: -0.1700
Data Index: 7944800 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.3538. Min Act: -0.1700
Data Index: 7693625 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.3538. Min Act: -0.1700
Data Index: 8261757 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.2913. Min Act: -0.1700
Data Index: 8352786 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.2600. Min Act: -0.1700
Data Index: 584316 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.2600. Min Act: -0.1700
Data Index: 6715378 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.2600. Min Act: -0.1700
Data Index: 8469966 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.2288. Min Act: -0.1700
Data Index: 4524150 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.2288. Min Act: -0.1700
Data Index: 6219037 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.1975. Min Act: -0.1700
Data Index: 4550417 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.1975. Min Act: -0.1700
Data Index: 4840988 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.2288. Min Act: -0.1700
Data Index: 8466110 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.1975. Min Act: -0.1700
Data Index: 7343368 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.1975. Min Act: -0.1700
Data Index: 2904471 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.1663. Min Act: -0.1700
Data Index: 5733402 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.1975. Min Act: -0.1700
Data Index: 578529 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5725. Min Range: -5.5725
Max Act: 5.1663. Min Act: -0.1700
Data Index: 5121945 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19