Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3667 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1705. Min Range: -6.1705
Max Act: 6.1705. Min Act: -0.1700
Data Index: 3184003 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1705. Min Range: -6.1705
Max Act: 6.1080. Min Act: -0.1700
Data Index: 3110590 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1705. Min Range: -6.1705
Max Act: 6.0455. Min Act: -0.1700
Data Index: 7586064 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1705. Min Range: -6.1705
Max Act: 6.0768. Min Act: -0.1700
Data Index: 3929780 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.9518. Min Act: -0.1700
Data Index: 4570564 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8893. Min Act: -0.1700
Data Index: 8123011 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8893. Min Act: -0.1700
Data Index: 5584681 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.9205. Min Act: -0.1700
Data Index: 4854033 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8580. Min Act: -0.1700
Data Index: 5318152 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.8580. Min Act: -0.1700
Data Index: 7196690 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.7955. Min Act: -0.1700
Data Index: 1112455 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.7955. Min Act: -0.1700
Data Index: 1124763 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.7643. Min Act: -0.1700
Data Index: 4996099 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.7643. Min Act: -0.1700
Data Index: 1387455 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.7330. Min Act: -0.1700
Data Index: 2223379 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.6705. Min Act: -0.1700
Data Index: 8255896 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.6705. Min Act: -0.1700
Data Index: 8040663 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.6705. Min Act: -0.1700
Data Index: 8437407 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.6393. Min Act: -0.1700
Data Index: 3136111 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1705. Min Range: -6.1705
Max Act: 5.6393. Min Act: -0.1700
Data Index: 566355 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19