Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4208 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.6109. Min Act: -0.1700
Data Index: 2235339 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.6109. Min Act: -0.1700
Data Index: 3477650 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.5484. Min Act: -0.1700
Data Index: 2889117 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.5484. Min Act: -0.1700
Data Index: 6525779 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 2231309 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 1406205 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 5567264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 5339825 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 1727580 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 5961517 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 4709219 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 3706871 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 7222756 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 2723678 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 5641417 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 4614816 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4859. Min Act: -0.1700
Data Index: 6510514 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.4234. Min Act: -0.1700
Data Index: 5711143 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.3609. Min Act: -0.1700
Data Index: 6462201 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6109. Min Range: -5.6109
Max Act: 5.3609. Min Act: -0.1700
Data Index: 2185320 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19