Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 728 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0977. Min Act: -0.1700
Data Index: 1114620 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0977. Min Act: -0.1700
Data Index: 1114622 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0802. Min Act: -0.1700
Data Index: 2276833 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0715. Min Act: -0.1700
Data Index: 3784883 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0540. Min Act: -0.1700
Data Index: 1030082 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0453. Min Act: -0.1700
Data Index: 4039777 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0453. Min Act: -0.1700
Data Index: 6707693 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0366. Min Act: -0.1700
Data Index: 5260027 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0366. Min Act: -0.1700
Data Index: 7007218 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0279. Min Act: -0.1700
Data Index: 1700731 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0279. Min Act: -0.1700
Data Index: 7734129 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0192. Min Act: -0.1700
Data Index: 1387916 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0192. Min Act: -0.1700
Data Index: 58495 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0192. Min Act: -0.1700
Data Index: 8320722 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0192. Min Act: -0.1700
Data Index: 3856332 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0105. Min Act: -0.1700
Data Index: 968871 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0105. Min Act: -0.1700
Data Index: 732248 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0018. Min Act: -0.1700
Data Index: 7469327 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0018. Min Act: -0.1700
Data Index: 127649 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0977. Min Range: -1.0977
Max Act: 1.0018. Min Act: -0.1700
Data Index: 6890286 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19