Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3619 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.9115. Min Act: -0.1700
Data Index: 5638939 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.4428. Min Act: -0.1699
Data Index: 500597 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.3490. Min Act: -0.1700
Data Index: 3170502 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.3178. Min Act: -0.1700
Data Index: 7261311 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.3803. Min Act: -0.1699
Data Index: 6846322 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.3490. Min Act: -0.1700
Data Index: 188913 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.3490. Min Act: -0.1700
Data Index: 4270735 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.3178. Min Act: -0.1700
Data Index: 6037319 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.2553. Min Act: -0.1700
Data Index: 2743910 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.3178. Min Act: -0.1700
Data Index: 1533676 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.2553. Min Act: -0.1700
Data Index: 6688736 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.2865. Min Act: -0.1700
Data Index: 4372859 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.2240. Min Act: -0.1700
Data Index: 5800517 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.2553. Min Act: -0.1699
Data Index: 3839497 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.2553. Min Act: -0.1700
Data Index: 5335743 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.2240. Min Act: -0.1700
Data Index: 3770139 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.2865. Min Act: -0.1700
Data Index: 1730224 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.2240. Min Act: -0.1700
Data Index: 4004428 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.2240. Min Act: -0.1700
Data Index: 5766726 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9115. Min Range: -6.9115
Max Act: 6.2240. Min Act: -0.1700
Data Index: 7125238 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19