Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1876 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1606. Min Range: -7.1606
Max Act: 7.1606. Min Act: -0.1700
Data Index: 7961347 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1606. Min Range: -7.1606
Max Act: 7.0043. Min Act: -0.1700
Data Index: 6263052 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.9418. Min Act: -0.1700
Data Index: 1411774 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.8481. Min Act: -0.1700
Data Index: 3515931 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.8168. Min Act: -0.1700
Data Index: 1016237 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.7856. Min Act: -0.1700
Data Index: 7219507 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.7856. Min Act: -0.1700
Data Index: 5110997 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.7543. Min Act: -0.1700
Data Index: 7789870 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.7543. Min Act: -0.1700
Data Index: 8421360 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.7231. Min Act: -0.1700
Data Index: 3122913 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.6606. Min Act: -0.1700
Data Index: 1146779 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.6606. Min Act: -0.1700
Data Index: 6964184 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.5981. Min Act: -0.1700
Data Index: 4537266 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.6293. Min Act: -0.1700
Data Index: 5598277 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.6293. Min Act: -0.1700
Data Index: 256075 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.5981. Min Act: -0.1700
Data Index: 7992280 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.5981. Min Act: -0.1700
Data Index: 7980650 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.5981. Min Act: -0.1700
Data Index: 685151 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.5668. Min Act: -0.1700
Data Index: 329288 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1606. Min Range: -7.1606
Max Act: 6.5668. Min Act: -0.1700
Data Index: 5404870 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #19