Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4338 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.2665. Min Act: -0.1700
Data Index: 6683906 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.2040. Min Act: -0.1700
Data Index: 6950147 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.2040. Min Act: -0.1700
Data Index: 8184410 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.2040. Min Act: -0.1700
Data Index: 953564 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.1728. Min Act: -0.1700
Data Index: 4268079 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.1415. Min Act: -0.1700
Data Index: 6822846 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.1103. Min Act: -0.1700
Data Index: 7764348 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.0790. Min Act: -0.1700
Data Index: 1341434 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.0790. Min Act: -0.1700
Data Index: 8498072 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.0790. Min Act: -0.1700
Data Index: 1224932 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.0790. Min Act: -0.1700
Data Index: 4387578 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.0478. Min Act: -0.1700
Data Index: 3185002 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.0478. Min Act: -0.1700
Data Index: 3391389 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.0478. Min Act: -0.1700
Data Index: 5587999 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.0165. Min Act: -0.1700
Data Index: 1016712 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.0165. Min Act: -0.1700
Data Index: 8091860 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2665. Min Range: -4.2665
Max Act: 4.0165. Min Act: -0.1700
Data Index: 932012 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.9852. Min Act: -0.1700
Data Index: 1796539 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.9540. Min Act: -0.1700
Data Index: 530216 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2665. Min Range: -4.2665
Max Act: 3.9540. Min Act: -0.1700
Data Index: 6255405 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #19