Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2948 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.5236. Min Act: -0.1700
Data Index: 1056455 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.5236. Min Act: -0.1700
Data Index: 5116871 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.4924. Min Act: -0.1700
Data Index: 4145236 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.4924. Min Act: -0.1700
Data Index: 280507 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.4611. Min Act: -0.1700
Data Index: 3791707 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.4611. Min Act: -0.1700
Data Index: 4255436 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.4299. Min Act: -0.1700
Data Index: 5274387 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.4611. Min Act: -0.1700
Data Index: 2682057 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.4299. Min Act: -0.1700
Data Index: 2741800 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.4299. Min Act: -0.1700
Data Index: 3798375 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.4299. Min Act: -0.1700
Data Index: 2735081 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.4299. Min Act: -0.1700
Data Index: 6217863 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.3986. Min Act: -0.1700
Data Index: 760576 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.3986. Min Act: -0.1700
Data Index: 5104526 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.3986. Min Act: -0.1700
Data Index: 6180725 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.3986. Min Act: -0.1700
Data Index: 211234 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.3986. Min Act: -0.1700
Data Index: 4759386 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.3986. Min Act: -0.1700
Data Index: 4666944 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.3986. Min Act: -0.1700
Data Index: 4561621 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5236. Min Range: -4.5236
Max Act: 4.3986. Min Act: -0.1700
Data Index: 3648748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19