Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2459 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2396. Min Range: -5.2396
Max Act: 5.2396. Min Act: -0.1700
Data Index: 5149498 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2396. Min Range: -5.2396
Max Act: 5.2084. Min Act: -0.1700
Data Index: 3269701 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2396. Min Range: -5.2396
Max Act: 5.1771. Min Act: -0.1700
Data Index: 8368306 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2396. Min Range: -5.2396
Max Act: 5.1146. Min Act: -0.1700
Data Index: 7296604 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2396. Min Range: -5.2396
Max Act: 5.0209. Min Act: -0.1700
Data Index: 6348767 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9896. Min Act: -0.1700
Data Index: 1204873 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9896. Min Act: -0.1700
Data Index: 177573 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9896. Min Act: -0.1700
Data Index: 5577742 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9584. Min Act: -0.1700
Data Index: 2937066 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9584. Min Act: -0.1700
Data Index: 5945022 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9584. Min Act: -0.1700
Data Index: 5015785 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9584. Min Act: -0.1700
Data Index: 4703886 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9271. Min Act: -0.1700
Data Index: 6613257 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9271. Min Act: -0.1700
Data Index: 7746421 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.8959. Min Act: -0.1700
Data Index: 5874655 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9271. Min Act: -0.1700
Data Index: 4562268 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9271. Min Act: -0.1700
Data Index: 3184424 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9271. Min Act: -0.1700
Data Index: 2024921 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.9271. Min Act: -0.1700
Data Index: 6420674 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2396. Min Range: -5.2396
Max Act: 4.8959. Min Act: -0.1700
Data Index: 6324184 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19