Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4004 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4434. Min Range: -8.4434
Max Act: 8.4434. Min Act: -0.1700
Data Index: 3313942 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4434. Min Range: -8.4434
Max Act: 8.3184. Min Act: -0.1700
Data Index: 2532988 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4434. Min Range: -8.4434
Max Act: 8.2559. Min Act: -0.1700
Data Index: 538161 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4434. Min Range: -8.4434
Max Act: 8.0997. Min Act: -0.1700
Data Index: 8507293 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.9434. Min Act: -0.1700
Data Index: 200370 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.7872. Min Act: -0.1700
Data Index: 5273743 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.8184. Min Act: -0.1700
Data Index: 5258892 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.7872. Min Act: -0.1700
Data Index: 6159539 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.8184. Min Act: -0.1700
Data Index: 2417964 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.7872. Min Act: -0.1700
Data Index: 6900420 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.7559. Min Act: -0.1700
Data Index: 3927369 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.7559. Min Act: -0.1700
Data Index: 6980922 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.6934. Min Act: -0.1700
Data Index: 6956198 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.6309. Min Act: -0.1700
Data Index: 3909833 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.6622. Min Act: -0.1700
Data Index: 2807626 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.6309. Min Act: -0.1700
Data Index: 6764507 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.6622. Min Act: -0.1700
Data Index: 5294053 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.5997. Min Act: -0.1700
Data Index: 8524075 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.6309. Min Act: -0.1700
Data Index: 2760634 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4434. Min Range: -8.4434
Max Act: 7.5684. Min Act: -0.1700
Data Index: 3102962 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19