Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1053 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2940. Min Range: -6.2940
Max Act: 6.2940. Min Act: -0.1700
Data Index: 6540155 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2940. Min Range: -6.2940
Max Act: 6.2627. Min Act: -0.1700
Data Index: 6690357 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2940. Min Range: -6.2940
Max Act: 6.0752. Min Act: -0.1700
Data Index: 615400 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2940. Min Range: -6.2940
Max Act: 6.1065. Min Act: -0.1700
Data Index: 1366301 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2940. Min Range: -6.2940
Max Act: 6.0752. Min Act: -0.1700
Data Index: 7832660 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.9815. Min Act: -0.1700
Data Index: 716674 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.9502. Min Act: -0.1700
Data Index: 3151631 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.9190. Min Act: -0.1700
Data Index: 3737734 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.9190. Min Act: -0.1700
Data Index: 8741360 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.8877. Min Act: -0.1700
Data Index: 4716843 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.8877. Min Act: -0.1700
Data Index: 760125 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.9190. Min Act: -0.1700
Data Index: 82008 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.8565. Min Act: -0.1700
Data Index: 5816235 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.8565. Min Act: -0.1700
Data Index: 4574993 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.8565. Min Act: -0.1700
Data Index: 4079594 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.8252. Min Act: -0.1700
Data Index: 218304 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.8252. Min Act: -0.1700
Data Index: 8780938 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.8252. Min Act: -0.1700
Data Index: 1366302 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.8252. Min Act: -0.1700
Data Index: 6653259 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2940. Min Range: -6.2940
Max Act: 5.7940. Min Act: -0.1700
Data Index: 2363035 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19