Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3263 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.5217. Min Act: -0.1700
Data Index: 8572803 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.5217. Min Act: -0.1700
Data Index: 6039533 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.4904. Min Act: -0.1700
Data Index: 7879922 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.5217. Min Act: -0.1700
Data Index: 5623817 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.3967. Min Act: -0.1700
Data Index: 1510611 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.3967. Min Act: -0.1700
Data Index: 1536514 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.3654. Min Act: -0.1700
Data Index: 730561 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.3654. Min Act: -0.1700
Data Index: 6788108 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.3342. Min Act: -0.1700
Data Index: 5523305 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.2717. Min Act: -0.1700
Data Index: 7390404 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.2404. Min Act: -0.1700
Data Index: 789026 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.2092. Min Act: -0.1700
Data Index: 7251281 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.1467. Min Act: -0.1700
Data Index: 1370488 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.1467. Min Act: -0.1700
Data Index: 7362936 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.1467. Min Act: -0.1700
Data Index: 3629120 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.1154. Min Act: -0.1700
Data Index: 2305702 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.1154. Min Act: -0.1700
Data Index: 1917863 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.0842. Min Act: -0.1700
Data Index: 3701838 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.1154. Min Act: -0.1700
Data Index: 7886900 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5217. Min Range: -5.5217
Max Act: 5.0842. Min Act: -0.1700
Data Index: 1529938 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #19