Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3178 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.4571. Min Act: -0.1700
Data Index: 4636460 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.2696. Min Act: -0.1700
Data Index: 1395517 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.2383. Min Act: -0.1700
Data Index: 7318894 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.2071. Min Act: -0.1700
Data Index: 7799153 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.2071. Min Act: -0.1700
Data Index: 4034591 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.1446. Min Act: -0.1700
Data Index: 7986656 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.1133. Min Act: -0.1700
Data Index: 804528 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.1133. Min Act: -0.1700
Data Index: 2105244 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.1133. Min Act: -0.1700
Data Index: 8630650 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.0508. Min Act: -0.1700
Data Index: 7339340 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.0508. Min Act: -0.1700
Data Index: 7491890 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.0508. Min Act: -0.1700
Data Index: 203161 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.0508. Min Act: -0.1700
Data Index: 3973577 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.0508. Min Act: -0.1700
Data Index: 4942407 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.0508. Min Act: -0.1700
Data Index: 5206067 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.0508. Min Act: -0.1700
Data Index: 3755201 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.0508. Min Act: -0.1700
Data Index: 2547881 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4571. Min Range: -6.4571
Max Act: 5.9883. Min Act: -0.1700
Data Index: 4024938 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4571. Min Range: -6.4571
Max Act: 5.9883. Min Act: -0.1700
Data Index: 2276293 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4571. Min Range: -6.4571
Max Act: 6.0196. Min Act: -0.1700
Data Index: 6642437 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19