Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1978 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.4467. Min Act: -0.1700
Data Index: 5121510 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.3842. Min Act: -0.1700
Data Index: 3865494 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.3217. Min Act: -0.1700
Data Index: 7649180 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.2904. Min Act: -0.1700
Data Index: 7002040 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.2904. Min Act: -0.1700
Data Index: 3691370 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1967. Min Act: -0.1700
Data Index: 8323201 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.2279. Min Act: -0.1700
Data Index: 4147103 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.2279. Min Act: -0.1700
Data Index: 4349112 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1967. Min Act: -0.1700
Data Index: 7657221 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1342. Min Act: -0.1700
Data Index: 8299062 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1342. Min Act: -0.1700
Data Index: 1310730 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1654. Min Act: -0.1700
Data Index: 6561220 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1342. Min Act: -0.1700
Data Index: 8779033 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1029. Min Act: -0.1700
Data Index: 3297124 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1029. Min Act: -0.1700
Data Index: 7981020 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1342. Min Act: -0.1700
Data Index: 6268221 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1342. Min Act: -0.1700
Data Index: 1812977 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1342. Min Act: -0.1700
Data Index: 4875007 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1029. Min Act: -0.1700
Data Index: 7355731 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4467. Min Range: -5.4467
Max Act: 5.1029. Min Act: -0.1700
Data Index: 1105951 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19