Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6077 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0896. Min Range: -5.0896
Max Act: 5.0896. Min Act: -0.1700
Data Index: 3492683 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0896. Min Range: -5.0896
Max Act: 5.0896. Min Act: -0.1700
Data Index: 4169097 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0896. Min Range: -5.0896
Max Act: 5.0896. Min Act: -0.1700
Data Index: 1917176 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0896. Min Range: -5.0896
Max Act: 5.0896. Min Act: -0.1700
Data Index: 421337 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0896. Min Range: -5.0896
Max Act: 5.0583. Min Act: -0.1700
Data Index: 7642063 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0896. Min Range: -5.0896
Max Act: 5.0583. Min Act: -0.1700
Data Index: 598004 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0896. Min Range: -5.0896
Max Act: 5.0271. Min Act: -0.1700
Data Index: 5924684 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.9958. Min Act: -0.1700
Data Index: 104107 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.9646. Min Act: -0.1700
Data Index: 5634049 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.9646. Min Act: -0.1700
Data Index: 3279608 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.9646. Min Act: -0.1700
Data Index: 8005085 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.9333. Min Act: -0.1700
Data Index: 8657348 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.9333. Min Act: -0.1700
Data Index: 7017449 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.9333. Min Act: -0.1700
Data Index: 3146432 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.8708. Min Act: -0.1700
Data Index: 6320122 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.8396. Min Act: -0.1700
Data Index: 1104532 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.8708. Min Act: -0.1700
Data Index: 5924683 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.9021. Min Act: -0.1700
Data Index: 2517958 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.8708. Min Act: -0.1700
Data Index: 5974654 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0896. Min Range: -5.0896
Max Act: 4.8708. Min Act: -0.1700
Data Index: 4764577 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19