Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.9749. Min Act: -0.1700
Data Index: 3937632 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.8499. Min Act: -0.1700
Data Index: 3280010 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.8186. Min Act: -0.1700
Data Index: 1399518 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.7873. Min Act: -0.1700
Data Index: 1786401 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.7873. Min Act: -0.1700
Data Index: 7918121 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.7873. Min Act: -0.1700
Data Index: 2158967 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.7873. Min Act: -0.1700
Data Index: 3250054 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.7560. Min Act: -0.1700
Data Index: 8502423 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.6935. Min Act: -0.1700
Data Index: 8282186 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.6935. Min Act: -0.1700
Data Index: 7844795 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.6935. Min Act: -0.1700
Data Index: 6033260 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.6935. Min Act: -0.1700
Data Index: 939177 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.6935. Min Act: -0.1700
Data Index: 4468965 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.6622. Min Act: -0.1700
Data Index: 1733289 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.6309. Min Act: -0.1700
Data Index: 3135302 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.6309. Min Act: -0.1700
Data Index: 335968 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.6309. Min Act: -0.1700
Data Index: 8824849 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.5683. Min Act: -0.1700
Data Index: 4691561 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.5996. Min Act: -0.1700
Data Index: 3600813 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9749. Min Range: -3.9749
Max Act: 3.5996. Min Act: -0.1700
Data Index: 3342187 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #19