Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3275 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.6215. Min Act: -0.1694
Data Index: 3391308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.4340. Min Act: -0.1700
Data Index: 608294 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.4028. Min Act: -0.1698
Data Index: 3748301 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.4028. Min Act: -0.1700
Data Index: 5404498 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.4028. Min Act: -0.1700
Data Index: 8025051 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3715. Min Act: -0.1700
Data Index: 3547268 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3715. Min Act: -0.1700
Data Index: 5514495 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3715. Min Act: -0.1700
Data Index: 2616438 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3715. Min Act: -0.1700
Data Index: 7683041 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3403. Min Act: -0.1700
Data Index: 2128857 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3403. Min Act: -0.1700
Data Index: 4488059 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3403. Min Act: -0.1700
Data Index: 642699 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3090. Min Act: -0.1700
Data Index: 4646889 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3090. Min Act: -0.1700
Data Index: 6849209 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3090. Min Act: -0.1700
Data Index: 6298861 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3090. Min Act: -0.1700
Data Index: 5984321 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3090. Min Act: -0.1699
Data Index: 1211675 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.3090. Min Act: -0.1699
Data Index: 762657 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.2778. Min Act: -0.1700
Data Index: 4907767 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6215. Min Range: -6.6215
Max Act: 6.2465. Min Act: -0.1697
Data Index: 1908878 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19