Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4352 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.4974. Min Act: -0.1700
Data Index: 2762948 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.4349. Min Act: -0.1700
Data Index: 7308315 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.3099. Min Act: -0.1700
Data Index: 4489747 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.2474. Min Act: -0.1700
Data Index: 4379401 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.1849. Min Act: -0.1700
Data Index: 726800 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.1849. Min Act: -0.1700
Data Index: 8362349 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.1849. Min Act: -0.1700
Data Index: 3324600 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.1849. Min Act: -0.1700
Data Index: 683529 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.1224. Min Act: -0.1700
Data Index: 5438316 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.1224. Min Act: -0.1700
Data Index: 7237863 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.1224. Min Act: -0.1700
Data Index: 2666175 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.1224. Min Act: -0.1700
Data Index: 8562265 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.1224. Min Act: -0.1700
Data Index: 5783447 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.1224. Min Act: -0.1700
Data Index: 6713322 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.0599. Min Act: -0.1700
Data Index: 6758872 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4974. Min Range: -9.4974
Max Act: 9.0599. Min Act: -0.1700
Data Index: 821472 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4974. Min Range: -9.4974
Max Act: 8.9349. Min Act: -0.1700
Data Index: 147890 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4974. Min Range: -9.4974
Max Act: 8.9349. Min Act: -0.1700
Data Index: 3721804 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4974. Min Range: -9.4974
Max Act: 8.9349. Min Act: -0.1700
Data Index: 3696578 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4974. Min Range: -9.4974
Max Act: 8.9349. Min Act: -0.1700
Data Index: 1412128 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #19