Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2370 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.7088. Min Act: -0.1700
Data Index: 6083425 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.7400. Min Act: -0.1700
Data Index: 7393383 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.6775. Min Act: -0.1700
Data Index: 2447450 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.5838. Min Act: -0.1700
Data Index: 2217610 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.5213. Min Act: -0.1700
Data Index: 7594785 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.5525. Min Act: -0.1700
Data Index: 596779 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.5525. Min Act: -0.1700
Data Index: 6310760 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.4588. Min Act: -0.1700
Data Index: 3405777 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.3963. Min Act: -0.1700
Data Index: 174768 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.4275. Min Act: -0.1700
Data Index: 5712110 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.3963. Min Act: -0.1700
Data Index: 1024510 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.3650. Min Act: -0.1700
Data Index: 4542176 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.3650. Min Act: -0.1700
Data Index: 5435717 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.3025. Min Act: -0.1700
Data Index: 1939335 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.3025. Min Act: -0.1700
Data Index: 7137278 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.3025. Min Act: -0.1700
Data Index: 4298156 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.2713. Min Act: -0.1700
Data Index: 379852 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.3025. Min Act: -0.1700
Data Index: 6709579 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.2400. Min Act: -0.1700
Data Index: 3634643 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7400. Min Range: -6.7400
Max Act: 6.3025. Min Act: -0.1700
Data Index: 1903309 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19