Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2024 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.8207. Min Act: -0.1700
Data Index: 5094199 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.7582. Min Act: -0.1700
Data Index: 7869555 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.7582. Min Act: -0.1700
Data Index: 181418 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.7582. Min Act: -0.1700
Data Index: 4389564 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.6332. Min Act: -0.1700
Data Index: 5979870 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.6957. Min Act: -0.1700
Data Index: 6406262 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.5707. Min Act: -0.1700
Data Index: 4062161 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.5707. Min Act: -0.1700
Data Index: 4059111 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.5082. Min Act: -0.1700
Data Index: 8196504 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.4457. Min Act: -0.1700
Data Index: 181413 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.4457. Min Act: -0.1700
Data Index: 2406292 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.3832. Min Act: -0.1700
Data Index: 3861042 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.3207. Min Act: -0.1700
Data Index: 3435122 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.3207. Min Act: -0.1700
Data Index: 8008766 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.3207. Min Act: -0.1700
Data Index: 6647172 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.3207. Min Act: -0.1700
Data Index: 2840436 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.2582. Min Act: -0.1700
Data Index: 3373302 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.2582. Min Act: -0.1700
Data Index: 181440 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.2582. Min Act: -0.1700
Data Index: 181411 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8207. Min Range: -9.8207
Max Act: 9.1957. Min Act: -0.1700
Data Index: 181415 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19