Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 958 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9838. Min Act: -0.1700
Data Index: 2967741 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9668. Min Act: -0.1700
Data Index: 8755280 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9838. Min Act: -0.1700
Data Index: 8013724 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9668. Min Act: -0.1641
Data Index: 6777565 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9668. Min Act: -0.1700
Data Index: 5352224 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9499. Min Act: -0.1696
Data Index: 2077677 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9499. Min Act: -0.1695
Data Index: 2575798 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9159. Min Act: -0.1663
Data Index: 2575782 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9329. Min Act: -0.1682
Data Index: 388831 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9159. Min Act: -0.1700
Data Index: 4585246 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.8988. Min Act: -0.1700
Data Index: 8121290 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.8988. Min Act: -0.1700
Data Index: 3908064 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9159. Min Act: -0.1700
Data Index: 704343 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9329. Min Act: -0.1700
Data Index: 123122 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.9159. Min Act: -0.1700
Data Index: 2301443 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.8988. Min Act: -0.1680
Data Index: 2575793 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.8988. Min Act: -0.1700
Data Index: 5414859 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.8988. Min Act: -0.1700
Data Index: 4210074 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.8988. Min Act: -0.1700
Data Index: 3854605 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9838. Min Range: -1.9838
Max Act: 1.8988. Min Act: -0.1700
Data Index: 8647142 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19