Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3182 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1722. Min Range: -9.1722
Max Act: 9.1722. Min Act: -0.1700
Data Index: 5461601 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1722. Min Range: -9.1722
Max Act: 9.1097. Min Act: -0.1700
Data Index: 1017195 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.9847. Min Act: -0.1700
Data Index: 7132124 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.9222. Min Act: -0.1700
Data Index: 8245356 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.7972. Min Act: -0.1700
Data Index: 2247154 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.7972. Min Act: -0.1700
Data Index: 7364230 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.7347. Min Act: -0.1700
Data Index: 3405775 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.6722. Min Act: -0.1700
Data Index: 3060672 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.6722. Min Act: -0.1700
Data Index: 7253853 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.6097. Min Act: -0.1700
Data Index: 8410740 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.6722. Min Act: -0.1700
Data Index: 6944932 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.5472. Min Act: -0.1700
Data Index: 4499624 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.5472. Min Act: -0.1700
Data Index: 1526005 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.4847. Min Act: -0.1700
Data Index: 665568 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.4847. Min Act: -0.1700
Data Index: 7059708 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.4847. Min Act: -0.1700
Data Index: 1260532 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.4847. Min Act: -0.1700
Data Index: 2938295 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.4222. Min Act: -0.1700
Data Index: 326701 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.3597. Min Act: -0.1700
Data Index: 2715664 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1722. Min Range: -9.1722
Max Act: 8.4222. Min Act: -0.1700
Data Index: 1518914 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19