Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3714 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.3856. Min Act: -0.1700
Data Index: 7968204 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.3231. Min Act: -0.1700
Data Index: 2554712 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.2606. Min Act: -0.1700
Data Index: 1771186 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.2606. Min Act: -0.1700
Data Index: 2871670 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.2606. Min Act: -0.1700
Data Index: 2511966 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.1981. Min Act: -0.1700
Data Index: 4494711 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.1981. Min Act: -0.1700
Data Index: 2679231 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.1981. Min Act: -0.1700
Data Index: 7914730 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.1981. Min Act: -0.1700
Data Index: 4708784 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.1981. Min Act: -0.1700
Data Index: 2661095 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.0731. Min Act: -0.1700
Data Index: 4244204 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.0731. Min Act: -0.1700
Data Index: 1711447 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.0731. Min Act: -0.1700
Data Index: 4708783 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.0731. Min Act: -0.1700
Data Index: 6840910 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.0731. Min Act: -0.1700
Data Index: 6238920 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.0731. Min Act: -0.1700
Data Index: 4235175 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.0106. Min Act: -0.1700
Data Index: 632251 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.0106. Min Act: -0.1700
Data Index: 721933 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.0106. Min Act: -0.1700
Data Index: 712991 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3856. Min Range: -8.3856
Max Act: 8.0106. Min Act: -0.1700
Data Index: 712990 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19