Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1829 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.8908. Min Act: -0.1700
Data Index: 7828501 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.7970. Min Act: -0.1700
Data Index: 2102867 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.7032. Min Act: -0.1700
Data Index: 5052209 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.7032. Min Act: -0.1700
Data Index: 6995125 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6406. Min Act: -0.1700
Data Index: 2730540 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6093. Min Act: -0.1700
Data Index: 479346 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6093. Min Act: -0.1700
Data Index: 2771017 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6093. Min Act: -0.1700
Data Index: 4907011 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6093. Min Act: -0.1700
Data Index: 5030438 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6093. Min Act: -0.1700
Data Index: 6285002 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6093. Min Act: -0.1700
Data Index: 957063 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.6093. Min Act: -0.1700
Data Index: 7545738 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5780. Min Act: -0.1700
Data Index: 1979258 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5780. Min Act: -0.1700
Data Index: 1503784 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5780. Min Act: -0.1700
Data Index: 4662930 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5780. Min Act: -0.1700
Data Index: 3789786 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5780. Min Act: -0.1700
Data Index: 7545734 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5780. Min Act: -0.1700
Data Index: 5346904 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5780. Min Act: -0.1700
Data Index: 5247020 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8908. Min Range: -3.8908
Max Act: 3.5780. Min Act: -0.1700
Data Index: 1939184 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19