Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5122 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.6054. Min Act: -0.1700
Data Index: 2139403 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.5429. Min Act: -0.1700
Data Index: 71542 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.4804. Min Act: -0.1700
Data Index: 2814592 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.5117. Min Act: -0.1700
Data Index: 3512784 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.4804. Min Act: -0.1700
Data Index: 450792 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.4804. Min Act: -0.1700
Data Index: 8796534 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.4179. Min Act: -0.1700
Data Index: 5286509 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.3867. Min Act: -0.1700
Data Index: 4679007 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.3867. Min Act: -0.1700
Data Index: 3786262 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.3554. Min Act: -0.1700
Data Index: 895096 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.3867. Min Act: -0.1700
Data Index: 6569847 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.3242. Min Act: -0.1700
Data Index: 3263146 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.3554. Min Act: -0.1700
Data Index: 7311881 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.2929. Min Act: -0.1700
Data Index: 6263335 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.3242. Min Act: -0.1700
Data Index: 3876687 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.3242. Min Act: -0.1700
Data Index: 3533363 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.2929. Min Act: -0.1700
Data Index: 3932456 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.2617. Min Act: -0.1700
Data Index: 1891424 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.2617. Min Act: -0.1700
Data Index: 8211302 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6054. Min Range: -5.6054
Max Act: 5.2617. Min Act: -0.1700
Data Index: 8438395 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19