Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3920 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.9319. Min Act: -0.1700
Data Index: 8207531 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.9006. Min Act: -0.1700
Data Index: 7672812 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.9006. Min Act: -0.1700
Data Index: 3417595 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.8694. Min Act: -0.1700
Data Index: 7095131 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.9006. Min Act: -0.1700
Data Index: 1275335 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.9006. Min Act: -0.1700
Data Index: 2980348 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.8694. Min Act: -0.1700
Data Index: 7501001 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.8694. Min Act: -0.1700
Data Index: 8052031 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.8381. Min Act: -0.1700
Data Index: 4559414 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.8381. Min Act: -0.1700
Data Index: 1509860 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.8381. Min Act: -0.1700
Data Index: 6313563 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.7756. Min Act: -0.1700
Data Index: 3747673 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.8069. Min Act: -0.1700
Data Index: 7286178 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.7756. Min Act: -0.1700
Data Index: 5831606 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.7756. Min Act: -0.1700
Data Index: 4284164 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.7756. Min Act: -0.1700
Data Index: 7764314 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.7756. Min Act: -0.1700
Data Index: 3758899 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.7756. Min Act: -0.1700
Data Index: 7855289 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.7756. Min Act: -0.1700
Data Index: 6617024 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9319. Min Range: -4.9319
Max Act: 4.7444. Min Act: -0.1700
Data Index: 6141518 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #19