Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2434 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.5116. Min Act: -0.1483
Data Index: 5933160 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.4061. Min Act: -0.1379
Data Index: 3492753 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3797. Min Act: -0.1666
Data Index: 3869313 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3708. Min Act: -0.1690
Data Index: 2806221 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3620. Min Act: -0.1471
Data Index: 2275775 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3532. Min Act: -0.1409
Data Index: 5211653 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3532. Min Act: -0.1551
Data Index: 1436168 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3532. Min Act: -0.1501
Data Index: 3412712 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3356. Min Act: -0.1348
Data Index: 5877817 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3532. Min Act: -0.1214
Data Index: 5490649 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3444. Min Act: -0.1275
Data Index: 6435644 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3444. Min Act: -0.1596
Data Index: 4525085 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3267. Min Act: -0.1340
Data Index: 3265161 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3356. Min Act: -0.1417
Data Index: 8804803 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3356. Min Act: -0.1154
Data Index: 1202066 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3267. Min Act: -0.1680
Data Index: 3758745 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3267. Min Act: -0.1556
Data Index: 1135600 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3444. Min Act: -0.1579
Data Index: 5905381 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3267. Min Act: -0.1540
Data Index: 1057671 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5116. Min Range: -1.5116
Max Act: 1.3267. Min Act: -0.0998
Data Index: 4738302 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #19