Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1804 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2460. Min Range: -3.2460
Max Act: 3.2460. Min Act: -0.1700
Data Index: 6984801 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2460. Min Range: -3.2460
Max Act: 3.1831. Min Act: -0.1700
Data Index: 1169835 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2460. Min Range: -3.2460
Max Act: 3.1044. Min Act: -0.1700
Data Index: 5085949 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2460. Min Range: -3.2460
Max Act: 3.0571. Min Act: -0.1700
Data Index: 2329426 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2460. Min Range: -3.2460
Max Act: 3.0729. Min Act: -0.1700
Data Index: 8349313 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2460. Min Range: -3.2460
Max Act: 3.0413. Min Act: -0.1700
Data Index: 2623149 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2460. Min Range: -3.2460
Max Act: 3.0413. Min Act: -0.1700
Data Index: 7462202 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2460. Min Range: -3.2460
Max Act: 3.0413. Min Act: -0.1700
Data Index: 5974463 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2460. Min Range: -3.2460
Max Act: 3.0097. Min Act: -0.1700
Data Index: 5645742 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2460. Min Range: -3.2460
Max Act: 3.0097. Min Act: -0.1700
Data Index: 3331957 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2460. Min Range: -3.2460
Max Act: 2.9939. Min Act: -0.1700
Data Index: 8790152 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2460. Min Range: -3.2460
Max Act: 2.9939. Min Act: -0.1700
Data Index: 5085953 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2460. Min Range: -3.2460
Max Act: 2.9781. Min Act: -0.1700
Data Index: 400980 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2460. Min Range: -3.2460
Max Act: 2.9781. Min Act: -0.1700
Data Index: 1610122 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2460. Min Range: -3.2460
Max Act: 2.9781. Min Act: -0.1700
Data Index: 6222693 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2460. Min Range: -3.2460
Max Act: 2.9465. Min Act: -0.1700
Data Index: 8345316 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2460. Min Range: -3.2460
Max Act: 2.9623. Min Act: -0.1700
Data Index: 3345475 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2460. Min Range: -3.2460
Max Act: 2.9623. Min Act: -0.1700
Data Index: 2085062 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2460. Min Range: -3.2460
Max Act: 2.9465. Min Act: -0.1700
Data Index: 2754212 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2460. Min Range: -3.2460
Max Act: 2.9306. Min Act: -0.1700
Data Index: 4246305 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19