Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2853 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.1942. Min Act: -0.1700
Data Index: 4836196 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.1942. Min Act: -0.1700
Data Index: 2780811 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.1942. Min Act: -0.1700
Data Index: 2780812 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.1630. Min Act: -0.1700
Data Index: 6994108 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.1942. Min Act: -0.1700
Data Index: 118198 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.1317. Min Act: -0.1700
Data Index: 424268 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.1630. Min Act: -0.1700
Data Index: 2780810 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.1630. Min Act: -0.1700
Data Index: 1706212 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.1630. Min Act: -0.1700
Data Index: 6971432 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.1317. Min Act: -0.1700
Data Index: 2780809 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.1005. Min Act: -0.1700
Data Index: 4302130 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.0692. Min Act: -0.1700
Data Index: 3944042 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.0692. Min Act: -0.1700
Data Index: 3376650 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.0692. Min Act: -0.1700
Data Index: 4405320 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.0692. Min Act: -0.1700
Data Index: 7086958 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.0692. Min Act: -0.1700
Data Index: 3518477 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.0380. Min Act: -0.1700
Data Index: 3583137 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.0380. Min Act: -0.1700
Data Index: 8611553 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.0380. Min Act: -0.1700
Data Index: 4466163 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1942. Min Range: -5.1942
Max Act: 5.0380. Min Act: -0.1700
Data Index: 8812770 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19