Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3117 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.8902. Min Act: -0.1700
Data Index: 2536969 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.8590. Min Act: -0.1700
Data Index: 1053397 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.8902. Min Act: -0.1700
Data Index: 286085 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.8277. Min Act: -0.1700
Data Index: 22291 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.7652. Min Act: -0.1700
Data Index: 5030694 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.7652. Min Act: -0.1700
Data Index: 8789283 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.7340. Min Act: -0.1700
Data Index: 8191209 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.7340. Min Act: -0.1700
Data Index: 8494556 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.7027. Min Act: -0.1700
Data Index: 2352446 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.7027. Min Act: -0.1700
Data Index: 7562853 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.6715. Min Act: -0.1700
Data Index: 6254922 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.6715. Min Act: -0.1700
Data Index: 7150050 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.6402. Min Act: -0.1700
Data Index: 966841 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.6402. Min Act: -0.1700
Data Index: 3997768 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.6402. Min Act: -0.1700
Data Index: 242996 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.6090. Min Act: -0.1700
Data Index: 5846132 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.6090. Min Act: -0.1700
Data Index: 863828 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.6090. Min Act: -0.1700
Data Index: 87808 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.6402. Min Act: -0.1700
Data Index: 6410341 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8902. Min Range: -6.8902
Max Act: 6.5777. Min Act: -0.1700
Data Index: 866034 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #19