Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2857 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3079. Min Range: -6.3079
Max Act: 6.3079. Min Act: -0.1700
Data Index: 3111729 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3079. Min Range: -6.3079
Max Act: 6.1829. Min Act: -0.1700
Data Index: 5103786 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3079. Min Range: -6.3079
Max Act: 6.1204. Min Act: -0.1700
Data Index: 555608 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3079. Min Range: -6.3079
Max Act: 6.0891. Min Act: -0.1700
Data Index: 938485 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3079. Min Range: -6.3079
Max Act: 6.0579. Min Act: -0.1700
Data Index: 6942065 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3079. Min Range: -6.3079
Max Act: 6.0266. Min Act: -0.1700
Data Index: 3977598 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3079. Min Range: -6.3079
Max Act: 6.0266. Min Act: -0.1700
Data Index: 2056557 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.9329. Min Act: -0.1700
Data Index: 2229642 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.9329. Min Act: -0.1700
Data Index: 4223349 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.9016. Min Act: -0.1700
Data Index: 5275580 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.9016. Min Act: -0.1700
Data Index: 332415 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.9016. Min Act: -0.1700
Data Index: 8053982 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.9016. Min Act: -0.1700
Data Index: 3740474 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.8704. Min Act: -0.1700
Data Index: 6631274 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.8704. Min Act: -0.1700
Data Index: 1607971 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.8704. Min Act: -0.1700
Data Index: 6645183 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.8704. Min Act: -0.1700
Data Index: 8219345 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.8391. Min Act: -0.1700
Data Index: 7342649 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.8079. Min Act: -0.1700
Data Index: 193958 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3079. Min Range: -6.3079
Max Act: 5.8079. Min Act: -0.1700
Data Index: 1013650 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19