Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2733 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.1480. Min Act: -0.1700
Data Index: 648174 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0811. Min Act: -0.1700
Data Index: 6269901 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0811. Min Act: -0.1700
Data Index: 4210639 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0643. Min Act: -0.1700
Data Index: 1405406 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0643. Min Act: -0.1700
Data Index: 8635903 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0475. Min Act: -0.1700
Data Index: 937869 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0306. Min Act: -0.1700
Data Index: 8178647 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0475. Min Act: -0.1691
Data Index: 3973575 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0306. Min Act: -0.1700
Data Index: 4308151 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0306. Min Act: -0.1700
Data Index: 7488141 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0306. Min Act: -0.1700
Data Index: 1537812 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0138. Min Act: -0.1700
Data Index: 1472969 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0138. Min Act: -0.1700
Data Index: 1547637 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0138. Min Act: -0.1699
Data Index: 3767661 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1480. Min Range: -2.1480
Max Act: 2.0138. Min Act: -0.1697
Data Index: 2092807 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1480. Min Range: -2.1480
Max Act: 1.9969. Min Act: -0.1700
Data Index: 6112377 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1480. Min Range: -2.1480
Max Act: 1.9969. Min Act: -0.1700
Data Index: 3245303 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1480. Min Range: -2.1480
Max Act: 1.9969. Min Act: -0.1700
Data Index: 6750223 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1480. Min Range: -2.1480
Max Act: 1.9969. Min Act: -0.1700
Data Index: 907762 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1480. Min Range: -2.1480
Max Act: 1.9969. Min Act: -0.1700
Data Index: 3654264 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19