Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4852 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.6132. Min Act: -0.1700
Data Index: 4792198 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.5818. Min Act: -0.1700
Data Index: 8715385 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.5508. Min Act: -0.1667
Data Index: 7575921 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.5126. Min Act: -0.1699
Data Index: 2262064 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.5051. Min Act: -0.1700
Data Index: 2741019 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4901. Min Act: -0.1683
Data Index: 8391144 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4975. Min Act: -0.1700
Data Index: 8610773 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4975. Min Act: -0.1699
Data Index: 8072684 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4752. Min Act: -0.1700
Data Index: 6651508 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4826. Min Act: -0.1700
Data Index: 813498 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4752. Min Act: -0.1699
Data Index: 2759698 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4752. Min Act: -0.1699
Data Index: 821212 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4678. Min Act: -0.1699
Data Index: 5865178 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4678. Min Act: -0.1700
Data Index: 2922540 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4752. Min Act: -0.1699
Data Index: 5859938 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4604. Min Act: -0.1700
Data Index: 7236550 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4604. Min Act: -0.1700
Data Index: 6839989 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4604. Min Act: -0.1700
Data Index: 4223260 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4531. Min Act: -0.1694
Data Index: 940248 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6132. Min Range: -0.6132
Max Act: 0.4531. Min Act: -0.1673
Data Index: 8697433 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19