Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6076 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1564. Min Range: -5.1564
Max Act: 5.1564. Min Act: -0.1700
Data Index: 4877952 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1564. Min Range: -5.1564
Max Act: 5.0002. Min Act: -0.1700
Data Index: 1003135 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1564. Min Range: -5.1564
Max Act: 5.0002. Min Act: -0.1700
Data Index: 1400600 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1564. Min Range: -5.1564
Max Act: 5.0002. Min Act: -0.1700
Data Index: 7976165 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.9689. Min Act: -0.1700
Data Index: 1354762 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.9377. Min Act: -0.1700
Data Index: 2726646 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.9689. Min Act: -0.1700
Data Index: 7743101 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.9377. Min Act: -0.1700
Data Index: 7743102 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.9377. Min Act: -0.1700
Data Index: 1511809 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.9377. Min Act: -0.1700
Data Index: 86125 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.8752. Min Act: -0.1700
Data Index: 1429198 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.8752. Min Act: -0.1700
Data Index: 4938688 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.8752. Min Act: -0.1700
Data Index: 7523388 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.8752. Min Act: -0.1700
Data Index: 4031088 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.8127. Min Act: -0.1700
Data Index: 977999 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.8439. Min Act: -0.1700
Data Index: 4223472 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.8127. Min Act: -0.1700
Data Index: 5583354 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.8439. Min Act: -0.1700
Data Index: 5983041 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.8439. Min Act: -0.1700
Data Index: 1200350 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1564. Min Range: -5.1564
Max Act: 4.8127. Min Act: -0.1700
Data Index: 219954 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #19