Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.7311. Min Act: -0.1700
Data Index: 1593124 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.7311. Min Act: -0.1700
Data Index: 2503660 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.7311. Min Act: -0.1699
Data Index: 4290422 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.7311. Min Act: -0.1700
Data Index: 1399170 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.7225. Min Act: -0.1700
Data Index: 5468806 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.7051. Min Act: -0.1700
Data Index: 6509186 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6965. Min Act: -0.1687
Data Index: 486797 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.7051. Min Act: -0.1700
Data Index: 6664130 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6965. Min Act: -0.1700
Data Index: 2496661 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6965. Min Act: -0.1700
Data Index: 1135761 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6965. Min Act: -0.1700
Data Index: 3534846 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6791. Min Act: -0.1700
Data Index: 3830449 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6878. Min Act: -0.1700
Data Index: 6474938 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6791. Min Act: -0.1700
Data Index: 7623811 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6791. Min Act: -0.1699
Data Index: 5868021 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6791. Min Act: -0.1700
Data Index: 51568 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6791. Min Act: -0.1700
Data Index: 3137630 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6617. Min Act: -0.1700
Data Index: 3009237 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6704. Min Act: -0.1699
Data Index: 131700 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7311. Min Range: -1.7311
Max Act: 1.6617. Min Act: -0.1700
Data Index: 3395142 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19