Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2241 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2300. Min Range: -8.2300
Max Act: 8.2300. Min Act: -0.1700
Data Index: 838006 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2300. Min Range: -8.2300
Max Act: 8.1675. Min Act: -0.1700
Data Index: 1681707 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.8550. Min Act: -0.1700
Data Index: 3960558 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.7300. Min Act: -0.1700
Data Index: 427159 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.6050. Min Act: -0.1700
Data Index: 2057506 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.5425. Min Act: -0.1700
Data Index: 7189318 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.4175. Min Act: -0.1700
Data Index: 5138574 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.4175. Min Act: -0.1700
Data Index: 7364985 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.3862. Min Act: -0.1700
Data Index: 1082439 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.3862. Min Act: -0.1700
Data Index: 6269323 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.3862. Min Act: -0.1700
Data Index: 8159254 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.3550. Min Act: -0.1700
Data Index: 8153921 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.3237. Min Act: -0.1700
Data Index: 1377175 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.3237. Min Act: -0.1700
Data Index: 2073320 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.2925. Min Act: -0.1700
Data Index: 3260683 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.2925. Min Act: -0.1700
Data Index: 69603 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.2612. Min Act: -0.1700
Data Index: 35943 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.2300. Min Act: -0.1700
Data Index: 1128586 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.1987. Min Act: -0.1700
Data Index: 7940054 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2300. Min Range: -8.2300
Max Act: 7.1675. Min Act: -0.1700
Data Index: 7014644 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19