Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2397. Min Range: -6.2397
Max Act: 6.2085. Min Act: -0.1700
Data Index: 5128279 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2397. Min Range: -6.2397
Max Act: 6.2397. Min Act: -0.1700
Data Index: 4819775 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.9897. Min Act: -0.1700
Data Index: 7700615 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.9897. Min Act: -0.1700
Data Index: 3710731 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.9897. Min Act: -0.1700
Data Index: 8642404 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.9585. Min Act: -0.1700
Data Index: 1889442 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.9585. Min Act: -0.1700
Data Index: 4001308 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.8960. Min Act: -0.1700
Data Index: 750647 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.9272. Min Act: -0.1700
Data Index: 2091868 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.8647. Min Act: -0.1700
Data Index: 421539 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.8335. Min Act: -0.1700
Data Index: 832719 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.8647. Min Act: -0.1700
Data Index: 6510940 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.8335. Min Act: -0.1700
Data Index: 1959464 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.8022. Min Act: -0.1700
Data Index: 1889440 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.8335. Min Act: -0.1700
Data Index: 4017552 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.8335. Min Act: -0.1700
Data Index: 6767934 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.8022. Min Act: -0.1700
Data Index: 6076117 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.7710. Min Act: -0.1700
Data Index: 6839654 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.7397. Min Act: -0.1700
Data Index: 4180708 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2397. Min Range: -6.2397
Max Act: 5.7710. Min Act: -0.1700
Data Index: 5436588 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #19