Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4998 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0361. Min Range: -5.0361
Max Act: 5.0361. Min Act: -0.1700
Data Index: 8452294 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.9736. Min Act: -0.1700
Data Index: 7650801 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.9736. Min Act: -0.1700
Data Index: 3881876 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.9424. Min Act: -0.1700
Data Index: 1316034 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.9424. Min Act: -0.1700
Data Index: 3444168 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.9111. Min Act: -0.1700
Data Index: 4073520 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.8174. Min Act: -0.1700
Data Index: 1122096 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.8486. Min Act: -0.1700
Data Index: 5561577 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.8174. Min Act: -0.1700
Data Index: 412463 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.8174. Min Act: -0.1700
Data Index: 5413730 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.7861. Min Act: -0.1700
Data Index: 740794 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.7236. Min Act: -0.1700
Data Index: 4699573 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.7236. Min Act: -0.1700
Data Index: 6236730 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.7549. Min Act: -0.1700
Data Index: 8663764 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.7236. Min Act: -0.1700
Data Index: 453211 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.7236. Min Act: -0.1700
Data Index: 22965 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.7236. Min Act: -0.1700
Data Index: 5656383 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.7236. Min Act: -0.1700
Data Index: 848248 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.7236. Min Act: -0.1700
Data Index: 547431 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0361. Min Range: -5.0361
Max Act: 4.6924. Min Act: -0.1700
Data Index: 8284254 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #19