Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2846 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.9763. Min Act: -0.1700
Data Index: 2985825 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.8513. Min Act: -0.1700
Data Index: 5659179 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.7888. Min Act: -0.1700
Data Index: 3498361 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.6013. Min Act: -0.1700
Data Index: 1134503 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.5075. Min Act: -0.1700
Data Index: 4666475 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.5388. Min Act: -0.1700
Data Index: 237593 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.5075. Min Act: -0.1700
Data Index: 1615330 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.4763. Min Act: -0.1700
Data Index: 5893268 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.4763. Min Act: -0.1700
Data Index: 7714974 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.4450. Min Act: -0.1700
Data Index: 3447683 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.4450. Min Act: -0.1700
Data Index: 3555964 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.4450. Min Act: -0.1700
Data Index: 4751607 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.4138. Min Act: -0.1700
Data Index: 4614523 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.4138. Min Act: -0.1700
Data Index: 2928795 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.4138. Min Act: -0.1700
Data Index: 8434642 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.3825. Min Act: -0.1700
Data Index: 4558657 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.3513. Min Act: -0.1700
Data Index: 5413868 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.3200. Min Act: -0.1700
Data Index: 7764908 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.3513. Min Act: -0.1700
Data Index: 4500302 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9763. Min Range: -4.9763
Max Act: 4.3200. Min Act: -0.1700
Data Index: 3679555 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19