Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1230 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.6940. Min Act: -0.1700
Data Index: 5649436 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.6003. Min Act: -0.1700
Data Index: 5922997 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.5690. Min Act: -0.1700
Data Index: 2302770 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.5378. Min Act: -0.1700
Data Index: 578969 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.5378. Min Act: -0.1700
Data Index: 3665081 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.4440. Min Act: -0.1700
Data Index: 3188184 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.4753. Min Act: -0.1700
Data Index: 1180925 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.4440. Min Act: -0.1700
Data Index: 6998463 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.4128. Min Act: -0.1700
Data Index: 5181479 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.4128. Min Act: -0.1700
Data Index: 8401088 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.4128. Min Act: -0.1700
Data Index: 3225254 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.4128. Min Act: -0.1700
Data Index: 638962 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.3815. Min Act: -0.1700
Data Index: 1791181 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.3503. Min Act: -0.1700
Data Index: 7834406 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.3503. Min Act: -0.1700
Data Index: 4421536 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.3503. Min Act: -0.1700
Data Index: 6343163 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.3503. Min Act: -0.1700
Data Index: 6543529 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.3815. Min Act: -0.1700
Data Index: 1198309 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.3503. Min Act: -0.1700
Data Index: 6242820 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6940. Min Range: -4.6940
Max Act: 4.3190. Min Act: -0.1700
Data Index: 1162436 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19