Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5002 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.8599. Min Act: -0.1700
Data Index: 4152981 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.8911. Min Act: -0.1700
Data Index: 958823 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.8599. Min Act: -0.1700
Data Index: 7477697 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.8286. Min Act: -0.1700
Data Index: 2388647 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.8286. Min Act: -0.1700
Data Index: 1595598 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.8286. Min Act: -0.1700
Data Index: 815726 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.7974. Min Act: -0.1700
Data Index: 6574297 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.7349. Min Act: -0.1700
Data Index: 2008947 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.7349. Min Act: -0.1700
Data Index: 6574301 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.7349. Min Act: -0.1700
Data Index: 5572218 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.7036. Min Act: -0.1700
Data Index: 6574303 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.7036. Min Act: -0.1700
Data Index: 4511590 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.6724. Min Act: -0.1700
Data Index: 4235745 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.6411. Min Act: -0.1700
Data Index: 5511001 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.6724. Min Act: -0.1700
Data Index: 2286941 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5786. Min Act: -0.1700
Data Index: 5296664 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5786. Min Act: -0.1700
Data Index: 3454989 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5786. Min Act: -0.1700
Data Index: 6574294 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5786. Min Act: -0.1700
Data Index: 2094173 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8911. Min Range: -5.8911
Max Act: 5.5786. Min Act: -0.1700
Data Index: 196957 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #19