Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2806 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4668. Min Range: -7.4668
Max Act: 7.4668. Min Act: -0.1700
Data Index: 7192938 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4668. Min Range: -7.4668
Max Act: 7.3105. Min Act: -0.1700
Data Index: 5244719 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4668. Min Range: -7.4668
Max Act: 7.2480. Min Act: -0.1700
Data Index: 2052967 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4668. Min Range: -7.4668
Max Act: 7.1230. Min Act: -0.1700
Data Index: 278999 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4668. Min Range: -7.4668
Max Act: 7.0605. Min Act: -0.1700
Data Index: 3841614 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4668. Min Range: -7.4668
Max Act: 7.0605. Min Act: -0.1700
Data Index: 6578895 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4668. Min Range: -7.4668
Max Act: 7.0293. Min Act: -0.1700
Data Index: 8769236 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4668. Min Range: -7.4668
Max Act: 7.0293. Min Act: -0.1700
Data Index: 8392436 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4668. Min Range: -7.4668
Max Act: 6.9355. Min Act: -0.1700
Data Index: 123750 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4668. Min Range: -7.4668
Max Act: 6.9355. Min Act: -0.1700
Data Index: 6201092 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4668. Min Range: -7.4668
Max Act: 6.9043. Min Act: -0.1700
Data Index: 21099 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4668. Min Range: -7.4668
Max Act: 6.8730. Min Act: -0.1700
Data Index: 325945 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4668. Min Range: -7.4668
Max Act: 6.8105. Min Act: -0.1700
Data Index: 6200788 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4668. Min Range: -7.4668
Max Act: 6.7793. Min Act: -0.1700
Data Index: 5550414 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4668. Min Range: -7.4668
Max Act: 6.7168. Min Act: -0.1700
Data Index: 2339500 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4668. Min Range: -7.4668
Max Act: 6.7793. Min Act: -0.1700
Data Index: 206742 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4668. Min Range: -7.4668
Max Act: 6.7480. Min Act: -0.1700
Data Index: 1070585 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4668. Min Range: -7.4668
Max Act: 6.7168. Min Act: -0.1700
Data Index: 176813 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4668. Min Range: -7.4668
Max Act: 6.7168. Min Act: -0.1700
Data Index: 4121879 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4668. Min Range: -7.4668
Max Act: 6.6855. Min Act: -0.1700
Data Index: 3962378 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #19