Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 748 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8814. Min Act: -0.1700
Data Index: 2817577 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8501. Min Act: -0.1700
Data Index: 6306934 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8188. Min Act: -0.1700
Data Index: 6242285 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8501. Min Act: -0.1700
Data Index: 6636056 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.8188. Min Act: -0.1700
Data Index: 2156320 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7563. Min Act: -0.1700
Data Index: 3323868 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7875. Min Act: -0.1700
Data Index: 2741766 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7563. Min Act: -0.1700
Data Index: 3411982 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7563. Min Act: -0.1700
Data Index: 8610081 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7250. Min Act: -0.1700
Data Index: 5318518 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7250. Min Act: -0.1700
Data Index: 8688749 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7250. Min Act: -0.1700
Data Index: 3102367 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.7250. Min Act: -0.1700
Data Index: 2427436 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.6937. Min Act: -0.1700
Data Index: 7971656 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.6937. Min Act: -0.1700
Data Index: 5284471 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.6937. Min Act: -0.1700
Data Index: 8539548 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.6937. Min Act: -0.1700
Data Index: 7970632 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.6937. Min Act: -0.1700
Data Index: 2143063 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.6624. Min Act: -0.1700
Data Index: 47775 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8814. Min Range: -3.8814
Max Act: 3.6624. Min Act: -0.1700
Data Index: 3246551 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19