Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2636 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5705. Min Range: -9.5705
Max Act: 9.5705. Min Act: -0.1700
Data Index: 7870941 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5705. Min Range: -9.5705
Max Act: 9.1955. Min Act: -0.1700
Data Index: 7939610 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5705. Min Range: -9.5705
Max Act: 9.1955. Min Act: -0.1700
Data Index: 4506870 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5705. Min Range: -9.5705
Max Act: 9.1330. Min Act: -0.1700
Data Index: 8016709 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5705. Min Range: -9.5705
Max Act: 9.1330. Min Act: -0.1700
Data Index: 751710 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5705. Min Range: -9.5705
Max Act: 9.1330. Min Act: -0.1700
Data Index: 6466660 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5705. Min Range: -9.5705
Max Act: 9.1330. Min Act: -0.1700
Data Index: 2452670 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5705. Min Range: -9.5705
Max Act: 9.0080. Min Act: -0.1700
Data Index: 4492135 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5705. Min Range: -9.5705
Max Act: 8.9455. Min Act: -0.1700
Data Index: 5776401 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5705. Min Range: -9.5705
Max Act: 8.9455. Min Act: -0.1700
Data Index: 1055265 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5705. Min Range: -9.5705
Max Act: 8.9455. Min Act: -0.1700
Data Index: 4187325 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5705. Min Range: -9.5705
Max Act: 8.9455. Min Act: -0.1700
Data Index: 7792517 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5705. Min Range: -9.5705
Max Act: 8.8830. Min Act: -0.1700
Data Index: 8321583 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5705. Min Range: -9.5705
Max Act: 8.8830. Min Act: -0.1700
Data Index: 7954599 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5705. Min Range: -9.5705
Max Act: 8.8830. Min Act: -0.1700
Data Index: 2412006 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5705. Min Range: -9.5705
Max Act: 8.7580. Min Act: -0.1700
Data Index: 2258924 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5705. Min Range: -9.5705
Max Act: 8.7580. Min Act: -0.1700
Data Index: 4702753 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5705. Min Range: -9.5705
Max Act: 8.7580. Min Act: -0.1700
Data Index: 665497 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5705. Min Range: -9.5705
Max Act: 8.7580. Min Act: -0.1700
Data Index: 3640563 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5705. Min Range: -9.5705
Max Act: 8.7580. Min Act: -0.1700
Data Index: 7837463 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19