Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 296 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.6012. Min Act: -0.1700
Data Index: 6996584 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.5699. Min Act: -0.1700
Data Index: 388578 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.5387. Min Act: -0.1700
Data Index: 4582544 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.5074. Min Act: -0.1700
Data Index: 6380573 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.5074. Min Act: -0.1700
Data Index: 6235666 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4762. Min Act: -0.1700
Data Index: 2173623 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.5074. Min Act: -0.1700
Data Index: 4288169 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4762. Min Act: -0.1700
Data Index: 2005661 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4762. Min Act: -0.1700
Data Index: 129678 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4762. Min Act: -0.1700
Data Index: 378275 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4762. Min Act: -0.1700
Data Index: 7117104 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4449. Min Act: -0.1700
Data Index: 2000180 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4762. Min Act: -0.1700
Data Index: 1745658 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4449. Min Act: -0.1700
Data Index: 6286240 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4137. Min Act: -0.1700
Data Index: 2549099 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4449. Min Act: -0.1700
Data Index: 4011853 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4449. Min Act: -0.1700
Data Index: 6572466 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4449. Min Act: -0.1700
Data Index: 2720861 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4137. Min Act: -0.1700
Data Index: 5317736 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6012. Min Range: -6.6012
Max Act: 6.4137. Min Act: -0.1700
Data Index: 2626139 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #19