Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1680 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.7846. Min Act: -0.1700
Data Index: 834836 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.7221. Min Act: -0.1700
Data Index: 1631191 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.6909. Min Act: -0.1700
Data Index: 1613171 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.6596. Min Act: -0.1700
Data Index: 6411459 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.6596. Min Act: -0.1700
Data Index: 5311739 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.5971. Min Act: -0.1700
Data Index: 125966 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.5659. Min Act: -0.1700
Data Index: 6111399 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.5034. Min Act: -0.1700
Data Index: 793174 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.5346. Min Act: -0.1700
Data Index: 2989114 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.5346. Min Act: -0.1700
Data Index: 681293 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.4721. Min Act: -0.1700
Data Index: 5092615 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.5346. Min Act: -0.1700
Data Index: 139401 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.5034. Min Act: -0.1700
Data Index: 982134 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.4721. Min Act: -0.1700
Data Index: 1181779 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.4409. Min Act: -0.1700
Data Index: 1191380 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.4096. Min Act: -0.1700
Data Index: 8077499 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.3784. Min Act: -0.1700
Data Index: 460363 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.3784. Min Act: -0.1700
Data Index: 3729421 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.3784. Min Act: -0.1700
Data Index: 8425005 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7846. Min Range: -5.7846
Max Act: 5.3471. Min Act: -0.1700
Data Index: 4678742 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19