Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.3278. Min Act: -0.1700
Data Index: 2192586 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.2336. Min Act: -0.1700
Data Index: 7510495 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.2022. Min Act: -0.1700
Data Index: 7586195 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.1707. Min Act: -0.1700
Data Index: 1745560 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.1707. Min Act: -0.1700
Data Index: 3941560 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.1864. Min Act: -0.1700
Data Index: 8821394 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.1707. Min Act: -0.1700
Data Index: 1964433 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.1550. Min Act: -0.1700
Data Index: 6391656 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.1392. Min Act: -0.1700
Data Index: 5240737 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.1707. Min Act: -0.1700
Data Index: 2655320 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.1392. Min Act: -0.1700
Data Index: 7123426 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.1235. Min Act: -0.1700
Data Index: 8821392 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.1077. Min Act: -0.1700
Data Index: 929157 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.1077. Min Act: -0.1700
Data Index: 6743777 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.0604. Min Act: -0.1700
Data Index: 3917725 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.0604. Min Act: -0.1700
Data Index: 676629 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.0604. Min Act: -0.1700
Data Index: 8829779 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.0447. Min Act: -0.1700
Data Index: 5307108 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.0289. Min Act: -0.1700
Data Index: 626357 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3278. Min Range: -3.3278
Max Act: 3.0131. Min Act: -0.1700
Data Index: 7362450 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #19