Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2073. Min Range: -6.2073
Max Act: 6.2073. Min Act: -0.1700
Data Index: 5470174 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2073. Min Range: -6.2073
Max Act: 6.0823. Min Act: -0.1700
Data Index: 66212 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2073. Min Range: -6.2073
Max Act: 6.1135. Min Act: -0.1700
Data Index: 7703850 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2073. Min Range: -6.2073
Max Act: 6.0510. Min Act: -0.1700
Data Index: 2088904 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.9573. Min Act: -0.1700
Data Index: 1470159 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.9260. Min Act: -0.1700
Data Index: 5967085 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.9573. Min Act: -0.1700
Data Index: 3579808 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.9573. Min Act: -0.1700
Data Index: 1494882 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.8948. Min Act: -0.1700
Data Index: 8796183 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.8948. Min Act: -0.1700
Data Index: 85475 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.8948. Min Act: -0.1700
Data Index: 5257916 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.8948. Min Act: -0.1700
Data Index: 6484992 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.8948. Min Act: -0.1700
Data Index: 6491528 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.8010. Min Act: -0.1700
Data Index: 6076785 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.8635. Min Act: -0.1700
Data Index: 6766270 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.8010. Min Act: -0.1700
Data Index: 6217793 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.8010. Min Act: -0.1700
Data Index: 1059059 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.8010. Min Act: -0.1700
Data Index: 252216 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.7698. Min Act: -0.1700
Data Index: 7447698 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2073. Min Range: -6.2073
Max Act: 5.8323. Min Act: -0.1700
Data Index: 1857559 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19