Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4062 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2016. Min Range: -5.2016
Max Act: 5.2016. Min Act: -0.1700
Data Index: 2962009 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2016. Min Range: -5.2016
Max Act: 5.1078. Min Act: -0.1700
Data Index: 1056652 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.8891. Min Act: -0.1700
Data Index: 5783064 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.8578. Min Act: -0.1700
Data Index: 1553919 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.8578. Min Act: -0.1700
Data Index: 7040874 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.8266. Min Act: -0.1700
Data Index: 4662396 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.7953. Min Act: -0.1700
Data Index: 1808049 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.8578. Min Act: -0.1700
Data Index: 6646242 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.7641. Min Act: -0.1700
Data Index: 6902767 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.8266. Min Act: -0.1700
Data Index: 6170443 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.7953. Min Act: -0.1700
Data Index: 6646237 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.7641. Min Act: -0.1700
Data Index: 5263437 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.7641. Min Act: -0.1700
Data Index: 8690338 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.7641. Min Act: -0.1700
Data Index: 7946817 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.7641. Min Act: -0.1700
Data Index: 335274 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.7328. Min Act: -0.1700
Data Index: 8306192 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.7328. Min Act: -0.1700
Data Index: 6318311 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.7328. Min Act: -0.1700
Data Index: 7409581 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.7328. Min Act: -0.1700
Data Index: 13803 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2016. Min Range: -5.2016
Max Act: 4.7328. Min Act: -0.1700
Data Index: 2977185 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #19