Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1566 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.2711. Min Act: -0.1700
Data Index: 7052069 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.2546. Min Act: -0.1700
Data Index: 1480241 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.2215. Min Act: -0.1700
Data Index: 3423212 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.2215. Min Act: -0.1700
Data Index: 7281076 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.2381. Min Act: -0.1700
Data Index: 7199503 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.2215. Min Act: -0.1700
Data Index: 8106050 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.2050. Min Act: -0.1700
Data Index: 2052508 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.2050. Min Act: -0.1700
Data Index: 8349561 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.1884. Min Act: -0.1700
Data Index: 523246 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.2050. Min Act: -0.1700
Data Index: 7177646 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.1884. Min Act: -0.1700
Data Index: 7539207 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.2050. Min Act: -0.1700
Data Index: 1105014 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.1717. Min Act: -0.1700
Data Index: 4991739 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.1717. Min Act: -0.1700
Data Index: 861904 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.1717. Min Act: -0.1700
Data Index: 604512 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.1717. Min Act: -0.1700
Data Index: 8827281 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.1717. Min Act: -0.1700
Data Index: 5731293 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.1551. Min Act: -0.1700
Data Index: 1895668 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.1551. Min Act: -0.1700
Data Index: 6696100 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2711. Min Range: -2.2711
Max Act: 2.1384. Min Act: -0.1700
Data Index: 8084138 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19