Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3525 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.7423. Min Act: -0.1700
Data Index: 783933 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.6954. Min Act: -0.1700
Data Index: 5142320 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.6328. Min Act: -0.1700
Data Index: 1384300 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.6015. Min Act: -0.1700
Data Index: 487379 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.4762. Min Act: -0.1700
Data Index: 7450511 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.4449. Min Act: -0.1700
Data Index: 8355435 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.4449. Min Act: -0.1700
Data Index: 873209 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.4292. Min Act: -0.1700
Data Index: 2039395 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.4449. Min Act: -0.1700
Data Index: 3812419 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.4292. Min Act: -0.1700
Data Index: 2437834 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.3978. Min Act: -0.1700
Data Index: 1437869 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.3822. Min Act: -0.1700
Data Index: 6320093 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.3822. Min Act: -0.1700
Data Index: 612690 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.3822. Min Act: -0.1700
Data Index: 1630360 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.3665. Min Act: -0.1700
Data Index: 6464073 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.3665. Min Act: -0.1700
Data Index: 6506526 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.3508. Min Act: -0.1700
Data Index: 8116770 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.3508. Min Act: -0.1700
Data Index: 337887 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.3351. Min Act: -0.1700
Data Index: 2282952 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7423. Min Range: -3.7423
Max Act: 3.3508. Min Act: -0.1700
Data Index: 7783146 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19