Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2246 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.7032. Min Act: -0.1700
Data Index: 2694773 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.7344. Min Act: -0.1700
Data Index: 5157741 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.6094. Min Act: -0.1700
Data Index: 911818 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.6094. Min Act: -0.1700
Data Index: 6628286 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.6094. Min Act: -0.1700
Data Index: 1696591 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.5782. Min Act: -0.1700
Data Index: 2332202 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.5782. Min Act: -0.1700
Data Index: 919580 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.5782. Min Act: -0.1700
Data Index: 3015168 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.5157. Min Act: -0.1700
Data Index: 6370748 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.5157. Min Act: -0.1700
Data Index: 4505041 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.5157. Min Act: -0.1700
Data Index: 4149412 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.4844. Min Act: -0.1700
Data Index: 536863 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.4844. Min Act: -0.1700
Data Index: 89344 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.4844. Min Act: -0.1700
Data Index: 7347740 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.4532. Min Act: -0.1700
Data Index: 1201532 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.4532. Min Act: -0.1700
Data Index: 2465281 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.4532. Min Act: -0.1700
Data Index: 3421196 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.4532. Min Act: -0.1700
Data Index: 487360 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.4532. Min Act: -0.1700
Data Index: 4100739 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7344. Min Range: -5.7344
Max Act: 5.4532. Min Act: -0.1700
Data Index: 3973785 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19