Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3968 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.4087. Min Act: -0.1700
Data Index: 698893 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.3462. Min Act: -0.1700
Data Index: 3104800 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.3150. Min Act: -0.1700
Data Index: 8489570 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.2837. Min Act: -0.1700
Data Index: 4705388 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.2212. Min Act: -0.1700
Data Index: 1465458 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.2212. Min Act: -0.1700
Data Index: 2868157 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.2212. Min Act: -0.1700
Data Index: 975384 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.1900. Min Act: -0.1700
Data Index: 6694221 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.1900. Min Act: -0.1700
Data Index: 5106496 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.1587. Min Act: -0.1700
Data Index: 4265176 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.1587. Min Act: -0.1700
Data Index: 4197411 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.1275. Min Act: -0.1700
Data Index: 6394251 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.1275. Min Act: -0.1700
Data Index: 366053 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.1275. Min Act: -0.1700
Data Index: 3735343 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.1275. Min Act: -0.1700
Data Index: 5652969 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.0650. Min Act: -0.1700
Data Index: 1073193 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.0962. Min Act: -0.1700
Data Index: 6610543 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.0337. Min Act: -0.1700
Data Index: 7850359 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.0650. Min Act: -0.1700
Data Index: 7690810 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4087. Min Range: -5.4087
Max Act: 5.0962. Min Act: -0.1700
Data Index: 8036027 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #19