Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2498 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.8911. Min Act: -0.1700
Data Index: 435294 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.8286. Min Act: -0.1700
Data Index: 435293 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.7036. Min Act: -0.1700
Data Index: 5428517 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.7036. Min Act: -0.1700
Data Index: 4085558 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.6724. Min Act: -0.1700
Data Index: 5428516 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.6411. Min Act: -0.1700
Data Index: 5318238 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.6724. Min Act: -0.1700
Data Index: 4085557 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.5786. Min Act: -0.1700
Data Index: 6709627 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.5786. Min Act: -0.1700
Data Index: 6679010 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.5161. Min Act: -0.1700
Data Index: 7713759 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.5161. Min Act: -0.1700
Data Index: 5846144 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.5161. Min Act: -0.1700
Data Index: 4244356 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.5474. Min Act: -0.1700
Data Index: 8076809 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.4849. Min Act: -0.1700
Data Index: 2699927 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.4536. Min Act: -0.1700
Data Index: 3886547 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.4536. Min Act: -0.1700
Data Index: 7006047 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.4224. Min Act: -0.1700
Data Index: 1988060 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.4224. Min Act: -0.1700
Data Index: 5450489 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.4536. Min Act: -0.1700
Data Index: 1820585 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8911. Min Range: -4.8911
Max Act: 4.3911. Min Act: -0.1700
Data Index: 445657 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #19