Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3668 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6020. Min Range: -7.6020
Max Act: 7.6020. Min Act: -0.1700
Data Index: 1185035 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6020. Min Range: -7.6020
Max Act: 7.4770. Min Act: -0.1700
Data Index: 6814295 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6020. Min Range: -7.6020
Max Act: 7.2895. Min Act: -0.1700
Data Index: 1328394 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6020. Min Range: -7.6020
Max Act: 7.2895. Min Act: -0.1700
Data Index: 6283566 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.9458. Min Act: -0.1700
Data Index: 4673991 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.8520. Min Act: -0.1700
Data Index: 727981 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.7895. Min Act: -0.1700
Data Index: 5325929 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.8208. Min Act: -0.1700
Data Index: 6458235 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.7270. Min Act: -0.1700
Data Index: 5207636 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.7270. Min Act: -0.1700
Data Index: 5849780 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.7270. Min Act: -0.1700
Data Index: 207376 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.6645. Min Act: -0.1700
Data Index: 3984749 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.6645. Min Act: -0.1700
Data Index: 3354680 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.6645. Min Act: -0.1700
Data Index: 7077528 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.6645. Min Act: -0.1700
Data Index: 7466988 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.6333. Min Act: -0.1700
Data Index: 3357703 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.6333. Min Act: -0.1700
Data Index: 5022519 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.6020. Min Act: -0.1700
Data Index: 6675532 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.6020. Min Act: -0.1700
Data Index: 4368985 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6020. Min Range: -7.6020
Max Act: 6.6333. Min Act: -0.1700
Data Index: 5616440 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19