Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 595 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3058. Min Range: -6.3058
Max Act: 6.3058. Min Act: -0.1700
Data Index: 841116 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3058. Min Range: -6.3058
Max Act: 6.2120. Min Act: -0.1700
Data Index: 8358994 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3058. Min Range: -6.3058
Max Act: 6.1808. Min Act: -0.1700
Data Index: 6221717 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3058. Min Range: -6.3058
Max Act: 6.1495. Min Act: -0.1700
Data Index: 5592490 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3058. Min Range: -6.3058
Max Act: 6.0558. Min Act: -0.1700
Data Index: 435411 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3058. Min Range: -6.3058
Max Act: 6.0558. Min Act: -0.1700
Data Index: 4035702 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3058. Min Range: -6.3058
Max Act: 6.0870. Min Act: -0.1700
Data Index: 7420167 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3058. Min Range: -6.3058
Max Act: 6.0558. Min Act: -0.1700
Data Index: 599580 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3058. Min Range: -6.3058
Max Act: 5.9933. Min Act: -0.1700
Data Index: 250656 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3058. Min Range: -6.3058
Max Act: 5.9933. Min Act: -0.1700
Data Index: 1502235 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3058. Min Range: -6.3058
Max Act: 5.9933. Min Act: -0.1700
Data Index: 5318795 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3058. Min Range: -6.3058
Max Act: 5.8995. Min Act: -0.1700
Data Index: 6460502 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3058. Min Range: -6.3058
Max Act: 5.8995. Min Act: -0.1700
Data Index: 6420608 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3058. Min Range: -6.3058
Max Act: 5.8995. Min Act: -0.1700
Data Index: 6235574 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3058. Min Range: -6.3058
Max Act: 5.8683. Min Act: -0.1700
Data Index: 3778576 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3058. Min Range: -6.3058
Max Act: 5.8370. Min Act: -0.1700
Data Index: 3783881 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3058. Min Range: -6.3058
Max Act: 5.8370. Min Act: -0.1700
Data Index: 5764732 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3058. Min Range: -6.3058
Max Act: 5.8058. Min Act: -0.1700
Data Index: 3009577 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3058. Min Range: -6.3058
Max Act: 5.8370. Min Act: -0.1700
Data Index: 1354904 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3058. Min Range: -6.3058
Max Act: 5.8370. Min Act: -0.1700
Data Index: 90088 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19