Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3613 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.7840. Min Act: -0.1700
Data Index: 3698242 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.6590. Min Act: -0.1700
Data Index: 5962232 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.6590. Min Act: -0.1700
Data Index: 4830068 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.5965. Min Act: -0.1700
Data Index: 6014554 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.5965. Min Act: -0.1700
Data Index: 4307854 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.5653. Min Act: -0.1700
Data Index: 6187655 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.5653. Min Act: -0.1700
Data Index: 2138728 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.5340. Min Act: -0.1700
Data Index: 8544730 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.5340. Min Act: -0.1700
Data Index: 7454116 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.5028. Min Act: -0.1700
Data Index: 189772 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.5028. Min Act: -0.1700
Data Index: 250660 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.5028. Min Act: -0.1700
Data Index: 810554 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.4715. Min Act: -0.1700
Data Index: 5421556 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.4715. Min Act: -0.1700
Data Index: 6698755 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.4715. Min Act: -0.1700
Data Index: 319457 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.4403. Min Act: -0.1700
Data Index: 954841 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.4403. Min Act: -0.1700
Data Index: 3014689 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.4090. Min Act: -0.1700
Data Index: 6980341 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.4090. Min Act: -0.1700
Data Index: 4523662 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7840. Min Range: -6.7840
Max Act: 6.4090. Min Act: -0.1700
Data Index: 4596960 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19