Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5777 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3065. Min Range: -7.3065
Max Act: 7.3065. Min Act: -0.1700
Data Index: 7506151 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3065. Min Range: -7.3065
Max Act: 7.2440. Min Act: -0.1700
Data Index: 2383560 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3065. Min Range: -7.3065
Max Act: 7.0878. Min Act: -0.1700
Data Index: 1211500 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3065. Min Range: -7.3065
Max Act: 7.0565. Min Act: -0.1700
Data Index: 6296971 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3065. Min Range: -7.3065
Max Act: 7.0565. Min Act: -0.1700
Data Index: 2118156 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3065. Min Range: -7.3065
Max Act: 7.0253. Min Act: -0.1700
Data Index: 4666925 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.9940. Min Act: -0.1700
Data Index: 3283150 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.9628. Min Act: -0.1700
Data Index: 7425893 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.9940. Min Act: -0.1700
Data Index: 4202410 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.9628. Min Act: -0.1700
Data Index: 5365642 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.9628. Min Act: -0.1700
Data Index: 4627501 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.9628. Min Act: -0.1700
Data Index: 7707237 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.8690. Min Act: -0.1700
Data Index: 6248963 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.9003. Min Act: -0.1700
Data Index: 5619877 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.9003. Min Act: -0.1700
Data Index: 5704491 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.9315. Min Act: -0.1700
Data Index: 4267125 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.8690. Min Act: -0.1700
Data Index: 6823278 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.8690. Min Act: -0.1700
Data Index: 6252871 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.9003. Min Act: -0.1700
Data Index: 5243915 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3065. Min Range: -7.3065
Max Act: 6.8065. Min Act: -0.1700
Data Index: 7269644 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19