Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4663 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.8869. Min Act: -0.1700
Data Index: 5284802 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.6994. Min Act: -0.1700
Data Index: 3791890 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.6681. Min Act: -0.1700
Data Index: 3917162 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.6681. Min Act: -0.1700
Data Index: 7389463 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.5744. Min Act: -0.1700
Data Index: 910540 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.5431. Min Act: -0.1700
Data Index: 7328846 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.5119. Min Act: -0.1700
Data Index: 6414509 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.4494. Min Act: -0.1700
Data Index: 7005312 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.4806. Min Act: -0.1700
Data Index: 8268379 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.4494. Min Act: -0.1700
Data Index: 1459104 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.4494. Min Act: -0.1700
Data Index: 1349725 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.4181. Min Act: -0.1700
Data Index: 935845 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.3556. Min Act: -0.1700
Data Index: 4004286 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.3869. Min Act: -0.1700
Data Index: 1384039 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.3556. Min Act: -0.1700
Data Index: 1400980 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.3244. Min Act: -0.1700
Data Index: 6389462 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2931. Min Act: -0.1700
Data Index: 1942611 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2931. Min Act: -0.1700
Data Index: 1375863 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2931. Min Act: -0.1700
Data Index: 5579053 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8869. Min Range: -6.8869
Max Act: 6.2931. Min Act: -0.1700
Data Index: 8084614 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19