Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2099 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1244. Min Range: -9.1244
Max Act: 9.1244. Min Act: -0.1700
Data Index: 3916660 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1244. Min Range: -9.1244
Max Act: 8.1244. Min Act: -0.1700
Data Index: 5212602 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1244. Min Range: -9.1244
Max Act: 8.0619. Min Act: -0.1700
Data Index: 1576306 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.9369. Min Act: -0.1700
Data Index: 2119159 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.7494. Min Act: -0.1700
Data Index: 7684268 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.6869. Min Act: -0.1700
Data Index: 5747360 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.5619. Min Act: -0.1700
Data Index: 2923810 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.5307. Min Act: -0.1700
Data Index: 8771628 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.5307. Min Act: -0.1700
Data Index: 3604137 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.4994. Min Act: -0.1700
Data Index: 6460710 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.4994. Min Act: -0.1700
Data Index: 6460711 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.4994. Min Act: -0.1700
Data Index: 2932294 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.4682. Min Act: -0.1700
Data Index: 8671913 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.4994. Min Act: -0.1700
Data Index: 1419179 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.4682. Min Act: -0.1700
Data Index: 7855716 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.4682. Min Act: -0.1700
Data Index: 1415019 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.4057. Min Act: -0.1700
Data Index: 5317455 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.4057. Min Act: -0.1700
Data Index: 4895141 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.4057. Min Act: -0.1700
Data Index: 5625895 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1244. Min Range: -9.1244
Max Act: 7.4057. Min Act: -0.1700
Data Index: 3194932 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19