Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3502 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6028. Min Range: -8.6028
Max Act: 8.6028. Min Act: -0.1700
Data Index: 4073024 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6028. Min Range: -8.6028
Max Act: 8.2278. Min Act: -0.1700
Data Index: 460411 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6028. Min Range: -8.6028
Max Act: 8.2903. Min Act: -0.1700
Data Index: 2412654 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6028. Min Range: -8.6028
Max Act: 8.0403. Min Act: -0.1700
Data Index: 2931959 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6028. Min Range: -8.6028
Max Act: 8.0403. Min Act: -0.1700
Data Index: 3787863 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.9778. Min Act: -0.1700
Data Index: 6394064 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.9778. Min Act: -0.1700
Data Index: 7752723 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.9778. Min Act: -0.1700
Data Index: 4073025 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.9778. Min Act: -0.1700
Data Index: 4623530 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.9153. Min Act: -0.1700
Data Index: 939672 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.9153. Min Act: -0.1700
Data Index: 7358237 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.8528. Min Act: -0.1700
Data Index: 7739261 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.8528. Min Act: -0.1700
Data Index: 2619253 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.8528. Min Act: -0.1700
Data Index: 1749429 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.8528. Min Act: -0.1700
Data Index: 6575480 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.8528. Min Act: -0.1700
Data Index: 5058804 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.7903. Min Act: -0.1700
Data Index: 4907944 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.7903. Min Act: -0.1700
Data Index: 7973216 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.7903. Min Act: -0.1700
Data Index: 7100672 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6028. Min Range: -8.6028
Max Act: 7.7278. Min Act: -0.1700
Data Index: 5508780 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #19