Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6016 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1224. Min Range: -9.1224
Max Act: 9.1224. Min Act: -0.1700
Data Index: 3896555 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.8099. Min Act: -0.1700
Data Index: 316700 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.4974. Min Act: -0.1700
Data Index: 6153807 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.4349. Min Act: -0.1700
Data Index: 6663408 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.3724. Min Act: -0.1700
Data Index: 4978735 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.3724. Min Act: -0.1700
Data Index: 5918058 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.3724. Min Act: -0.1700
Data Index: 7736958 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.3099. Min Act: -0.1700
Data Index: 3018641 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.3099. Min Act: -0.1700
Data Index: 8175598 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.3099. Min Act: -0.1700
Data Index: 1350693 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.3099. Min Act: -0.1700
Data Index: 6259288 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.3099. Min Act: -0.1700
Data Index: 571922 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.2474. Min Act: -0.1700
Data Index: 1900751 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.2474. Min Act: -0.1700
Data Index: 3426915 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.2474. Min Act: -0.1700
Data Index: 7840294 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.1849. Min Act: -0.1700
Data Index: 1742684 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.1849. Min Act: -0.1700
Data Index: 4941378 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.1224. Min Act: -0.1700
Data Index: 6309774 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.1224. Min Act: -0.1700
Data Index: 3745828 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1224. Min Range: -9.1224
Max Act: 8.0286. Min Act: -0.1700
Data Index: 5391344 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #19