Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.3118. Min Act: -0.1700
Data Index: 1907715 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.2332. Min Act: -0.1700
Data Index: 4430726 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.2804. Min Act: -0.1700
Data Index: 1753231 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.2332. Min Act: -0.1700
Data Index: 3404016 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.2647. Min Act: -0.1700
Data Index: 7328400 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.2489. Min Act: -0.1700
Data Index: 607308 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.2332. Min Act: -0.1700
Data Index: 8300628 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.2175. Min Act: -0.1700
Data Index: 6791946 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.2175. Min Act: -0.1700
Data Index: 3044802 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.1861. Min Act: -0.1700
Data Index: 2647939 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.1703. Min Act: -0.1700
Data Index: 2707528 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.2018. Min Act: -0.1700
Data Index: 2607971 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.2018. Min Act: -0.1700
Data Index: 6033966 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.1703. Min Act: -0.1700
Data Index: 4354337 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.1546. Min Act: -0.1700
Data Index: 1690881 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.1388. Min Act: -0.1700
Data Index: 2211131 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.1546. Min Act: -0.1700
Data Index: 5064476 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.1546. Min Act: -0.1700
Data Index: 5699943 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.1388. Min Act: -0.1700
Data Index: 5300546 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3118. Min Range: -3.3118
Max Act: 3.1231. Min Act: -0.1700
Data Index: 6712692 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19