Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2055 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1864. Min Range: -4.1864
Max Act: 4.1864. Min Act: -0.1700
Data Index: 1173297 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1864. Min Range: -4.1864
Max Act: 4.1551. Min Act: -0.1700
Data Index: 1865028 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1864. Min Range: -4.1864
Max Act: 4.1239. Min Act: -0.1700
Data Index: 5177502 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1864. Min Range: -4.1864
Max Act: 4.0613. Min Act: -0.1700
Data Index: 5445098 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1864. Min Range: -4.1864
Max Act: 4.0301. Min Act: -0.1700
Data Index: 8624524 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1864. Min Range: -4.1864
Max Act: 4.0613. Min Act: -0.1700
Data Index: 6536948 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.9988. Min Act: -0.1700
Data Index: 2228080 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.9988. Min Act: -0.1700
Data Index: 4328248 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.9676. Min Act: -0.1700
Data Index: 7474204 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.9676. Min Act: -0.1700
Data Index: 2775922 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.9363. Min Act: -0.1700
Data Index: 8308035 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.9363. Min Act: -0.1700
Data Index: 7843670 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.9050. Min Act: -0.1700
Data Index: 661507 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.9050. Min Act: -0.1700
Data Index: 1055353 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.9363. Min Act: -0.1700
Data Index: 8007468 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.9050. Min Act: -0.1700
Data Index: 7347727 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.8894. Min Act: -0.1700
Data Index: 1385274 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.8894. Min Act: -0.1700
Data Index: 5761741 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.8894. Min Act: -0.1700
Data Index: 432927 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1864. Min Range: -4.1864
Max Act: 3.8738. Min Act: -0.1700
Data Index: 7500871 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19