Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1087 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.3427. Min Act: -0.1700
Data Index: 7866720 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.3114. Min Act: -0.1700
Data Index: 7499067 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.2802. Min Act: -0.1700
Data Index: 5493712 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.1864. Min Act: -0.1700
Data Index: 5045947 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.1864. Min Act: -0.1700
Data Index: 1241019 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.0927. Min Act: -0.1700
Data Index: 4930019 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.1552. Min Act: -0.1700
Data Index: 787350 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.1239. Min Act: -0.1700
Data Index: 2770797 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.0927. Min Act: -0.1700
Data Index: 6211718 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.1239. Min Act: -0.1700
Data Index: 7904291 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.1239. Min Act: -0.1700
Data Index: 3140038 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.0927. Min Act: -0.1700
Data Index: 4581748 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.0302. Min Act: -0.1700
Data Index: 6591503 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.0614. Min Act: -0.1700
Data Index: 4464639 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.0302. Min Act: -0.1700
Data Index: 3287007 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.0302. Min Act: -0.1700
Data Index: 6510911 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.0302. Min Act: -0.1700
Data Index: 5648811 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3427. Min Range: -5.3427
Max Act: 5.0302. Min Act: -0.1700
Data Index: 3136336 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3427. Min Range: -5.3427
Max Act: 4.9989. Min Act: -0.1700
Data Index: 3494428 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3427. Min Range: -5.3427
Max Act: 4.9989. Min Act: -0.1700
Data Index: 2825241 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #19