Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 914 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0141. Min Range: -5.0141
Max Act: 5.0141. Min Act: -0.1700
Data Index: 3395524 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0141. Min Range: -5.0141
Max Act: 5.0141. Min Act: -0.1700
Data Index: 394663 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0141. Min Range: -5.0141
Max Act: 5.0141. Min Act: -0.1700
Data Index: 3784601 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0141. Min Range: -5.0141
Max Act: 5.0141. Min Act: -0.1700
Data Index: 4287325 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0141. Min Range: -5.0141
Max Act: 5.0141. Min Act: -0.1700
Data Index: 5376138 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0141. Min Range: -5.0141
Max Act: 5.0141. Min Act: -0.1700
Data Index: 3041158 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1700
Data Index: 2039907 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1700
Data Index: 1917715 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1700
Data Index: 1726730 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1700
Data Index: 1646795 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1700
Data Index: 1596233 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1700
Data Index: 1504429 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1700
Data Index: 261882 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1700
Data Index: 1325514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1700
Data Index: 1262536 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1700
Data Index: 965665 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1699
Data Index: 929722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9516. Min Act: -0.1700
Data Index: 836182 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1700
Data Index: 207638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0141. Min Range: -5.0141
Max Act: 4.9828. Min Act: -0.1700
Data Index: 731897 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19