Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 538 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3011. Min Range: -3.3011
Max Act: 3.3011. Min Act: -0.1700
Data Index: 1708589 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3011. Min Range: -3.3011
Max Act: 3.1282. Min Act: -0.1700
Data Index: 1744280 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3011. Min Range: -3.3011
Max Act: 3.0809. Min Act: -0.1700
Data Index: 5694880 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3011. Min Range: -3.3011
Max Act: 3.0020. Min Act: -0.1700
Data Index: 163031 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3011. Min Range: -3.3011
Max Act: 3.0020. Min Act: -0.1700
Data Index: 1136785 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3011. Min Range: -3.3011
Max Act: 3.0020. Min Act: -0.1700
Data Index: 1189935 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.9545. Min Act: -0.1700
Data Index: 702268 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.9070. Min Act: -0.1700
Data Index: 8279305 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.8753. Min Act: -0.1700
Data Index: 2896971 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.8276. Min Act: -0.1700
Data Index: 7556260 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.8435. Min Act: -0.1700
Data Index: 6411426 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.8435. Min Act: -0.1700
Data Index: 4801893 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.8435. Min Act: -0.1700
Data Index: 7788837 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.8117. Min Act: -0.1700
Data Index: 1621829 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.8117. Min Act: -0.1700
Data Index: 2449828 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.8117. Min Act: -0.1700
Data Index: 8103956 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.8117. Min Act: -0.1700
Data Index: 2654380 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.8117. Min Act: -0.1700
Data Index: 899320 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.8117. Min Act: -0.1700
Data Index: 2304475 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3011. Min Range: -3.3011
Max Act: 2.7798. Min Act: -0.1700
Data Index: 4186799 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #19