Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2855 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2944. Min Range: -7.2944
Max Act: 7.2944. Min Act: -0.1700
Data Index: 2586177 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2944. Min Range: -7.2944
Max Act: 7.2632. Min Act: -0.1700
Data Index: 6660327 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2944. Min Range: -7.2944
Max Act: 7.1694. Min Act: -0.1700
Data Index: 5844271 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2944. Min Range: -7.2944
Max Act: 7.1382. Min Act: -0.1700
Data Index: 4306107 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2944. Min Range: -7.2944
Max Act: 7.0444. Min Act: -0.1700
Data Index: 6556937 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2944. Min Range: -7.2944
Max Act: 7.0132. Min Act: -0.1700
Data Index: 5427386 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.9819. Min Act: -0.1700
Data Index: 4324104 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.8882. Min Act: -0.1700
Data Index: 7628235 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.8257. Min Act: -0.1700
Data Index: 6062345 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.8257. Min Act: -0.1700
Data Index: 6556495 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.7944. Min Act: -0.1700
Data Index: 4083175 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.6694. Min Act: -0.1700
Data Index: 7419663 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.6694. Min Act: -0.1700
Data Index: 1372811 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.6382. Min Act: -0.1700
Data Index: 1970327 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.6069. Min Act: -0.1700
Data Index: 5745133 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.6069. Min Act: -0.1700
Data Index: 6028123 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.5757. Min Act: -0.1700
Data Index: 8166081 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.5757. Min Act: -0.1700
Data Index: 2364062 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.5444. Min Act: -0.1700
Data Index: 1761327 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2944. Min Range: -7.2944
Max Act: 6.5444. Min Act: -0.1700
Data Index: 5379901 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19