Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2934 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.8964. Min Act: -0.1700
Data Index: 3828039 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.8453. Min Act: -0.1700
Data Index: 2116045 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.8200. Min Act: -0.1700
Data Index: 3820597 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.8116. Min Act: -0.1603
Data Index: 6890548 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.8032. Min Act: -0.1698
Data Index: 2696080 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7948. Min Act: -0.1700
Data Index: 6877809 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.8032. Min Act: -0.1700
Data Index: 1559063 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7781. Min Act: -0.1700
Data Index: 2200777 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7781. Min Act: -0.1677
Data Index: 5715987 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7781. Min Act: -0.1698
Data Index: 2555785 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7698. Min Act: -0.1697
Data Index: 2235651 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7532. Min Act: -0.1696
Data Index: 1309375 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7615. Min Act: -0.1700
Data Index: 7984521 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7698. Min Act: -0.1700
Data Index: 1433083 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7615. Min Act: -0.1699
Data Index: 6388808 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7615. Min Act: -0.1700
Data Index: 6325509 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7532. Min Act: -0.1699
Data Index: 2104745 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7615. Min Act: -0.1700
Data Index: 8704714 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7532. Min Act: -0.1700
Data Index: 6582137 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8964. Min Range: -0.8964
Max Act: 0.7532. Min Act: -0.1700
Data Index: 2421084 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19