Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2018 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7315. Min Range: -9.7315
Max Act: 9.7315. Min Act: -0.1700
Data Index: 6263727 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7315. Min Range: -9.7315
Max Act: 9.1065. Min Act: -0.1700
Data Index: 3813754 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7315. Min Range: -9.7315
Max Act: 9.0440. Min Act: -0.1700
Data Index: 8579017 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7315. Min Range: -9.7315
Max Act: 9.0440. Min Act: -0.1700
Data Index: 6127571 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7315. Min Range: -9.7315
Max Act: 9.0440. Min Act: -0.1700
Data Index: 8181578 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.9190. Min Act: -0.1700
Data Index: 4063733 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.8565. Min Act: -0.1700
Data Index: 6542305 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.8565. Min Act: -0.1700
Data Index: 6542304 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.7940. Min Act: -0.1700
Data Index: 2590219 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.7940. Min Act: -0.1700
Data Index: 5300934 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.7940. Min Act: -0.1700
Data Index: 196892 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.7940. Min Act: -0.1700
Data Index: 3813755 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.6690. Min Act: -0.1700
Data Index: 7250429 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.6690. Min Act: -0.1700
Data Index: 4004226 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.6690. Min Act: -0.1700
Data Index: 1505545 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.6065. Min Act: -0.1700
Data Index: 5916455 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.5440. Min Act: -0.1700
Data Index: 3236430 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.5440. Min Act: -0.1700
Data Index: 4688337 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.5440. Min Act: -0.1700
Data Index: 5687981 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7315. Min Range: -9.7315
Max Act: 8.5440. Min Act: -0.1700
Data Index: 2718308 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19