Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2447 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8571. Min Range: -11.8571
Max Act: 11.8571. Min Act: -0.1700
Data Index: 2087177 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8571. Min Range: -11.8571
Max Act: 11.8571. Min Act: -0.1698
Data Index: 8038878 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8571. Min Range: -11.8571
Max Act: 11.2946. Min Act: -0.1700
Data Index: 6684116 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.9821. Min Act: -0.1700
Data Index: 7060016 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.9196. Min Act: -0.1700
Data Index: 3895065 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.7946. Min Act: -0.1700
Data Index: 3176485 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.7321. Min Act: -0.1700
Data Index: 425594 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.8571. Min Act: -0.1700
Data Index: 5990243 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.7321. Min Act: -0.1700
Data Index: 4035867 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.6071. Min Act: -0.1700
Data Index: 1996227 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.5446. Min Act: -0.1700
Data Index: 2276629 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.5446. Min Act: -0.1700
Data Index: 8640770 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.5446. Min Act: -0.1700
Data Index: 6881671 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.4821. Min Act: -0.1700
Data Index: 1791581 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.4821. Min Act: -0.1700
Data Index: 2786117 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.4821. Min Act: -0.1700
Data Index: 4460782 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.4196. Min Act: -0.1700
Data Index: 8127122 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.4821. Min Act: -0.1700
Data Index: 4830759 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.3571. Min Act: -0.1700
Data Index: 822204 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8571. Min Range: -11.8571
Max Act: 10.3571. Min Act: -0.1700
Data Index: 792926 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19