Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5335 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.5128. Min Act: -0.1700
Data Index: 2087504 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.4503. Min Act: -0.1700
Data Index: 5799466 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.2628. Min Act: -0.1700
Data Index: 6329871 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.2003. Min Act: -0.1700
Data Index: 1559386 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.1690. Min Act: -0.1700
Data Index: 5590953 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.1065. Min Act: -0.1700
Data Index: 5862680 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.1065. Min Act: -0.1700
Data Index: 3646848 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.0753. Min Act: -0.1700
Data Index: 6748243 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.0753. Min Act: -0.1700
Data Index: 7555425 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.0753. Min Act: -0.1700
Data Index: 7682669 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.0753. Min Act: -0.1700
Data Index: 6107300 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.0440. Min Act: -0.1700
Data Index: 6748239 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.0440. Min Act: -0.1700
Data Index: 4284821 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.0753. Min Act: -0.1700
Data Index: 105620 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.0440. Min Act: -0.1700
Data Index: 6541939 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.0440. Min Act: -0.1700
Data Index: 6571146 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.0440. Min Act: -0.1700
Data Index: 7345226 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.0128. Min Act: -0.1700
Data Index: 3646849 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5128. Min Range: -7.5128
Max Act: 7.0128. Min Act: -0.1700
Data Index: 7161015 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5128. Min Range: -7.5128
Max Act: 6.9815. Min Act: -0.1700
Data Index: 6587641 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19