Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3285 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1827. Min Range: -5.1827
Max Act: 5.1827. Min Act: -0.1700
Data Index: 77295 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.8077. Min Act: -0.1700
Data Index: 713938 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.7139. Min Act: -0.1700
Data Index: 1575683 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.6826. Min Act: -0.1700
Data Index: 4673232 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.6514. Min Act: -0.1700
Data Index: 8818587 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.5889. Min Act: -0.1700
Data Index: 7564268 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.5576. Min Act: -0.1700
Data Index: 7882222 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.5264. Min Act: -0.1700
Data Index: 1527998 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.5264. Min Act: -0.1700
Data Index: 1403672 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.5264. Min Act: -0.1700
Data Index: 2601009 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.4951. Min Act: -0.1700
Data Index: 7767024 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.4951. Min Act: -0.1700
Data Index: 5731721 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.4951. Min Act: -0.1700
Data Index: 670575 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.4951. Min Act: -0.1700
Data Index: 2856952 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.4639. Min Act: -0.1700
Data Index: 4813937 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.4326. Min Act: -0.1700
Data Index: 7882225 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.4326. Min Act: -0.1700
Data Index: 267567 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.4326. Min Act: -0.1700
Data Index: 2252234 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.4326. Min Act: -0.1700
Data Index: 3533140 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1827. Min Range: -5.1827
Max Act: 4.4326. Min Act: -0.1700
Data Index: 2999053 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19