Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2257 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5294. Min Range: -8.5294
Max Act: 8.5294. Min Act: -0.1700
Data Index: 3967754 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.9044. Min Act: -0.1700
Data Index: 7430148 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.4981. Min Act: -0.1700
Data Index: 3874660 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.4356. Min Act: -0.1700
Data Index: 5366193 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.3731. Min Act: -0.1700
Data Index: 316250 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.3106. Min Act: -0.1700
Data Index: 355706 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.3106. Min Act: -0.1700
Data Index: 3105868 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.2794. Min Act: -0.1700
Data Index: 4825397 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.2481. Min Act: -0.1700
Data Index: 1053685 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.2169. Min Act: -0.1700
Data Index: 5043436 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.1544. Min Act: -0.1700
Data Index: 1892432 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.1231. Min Act: -0.1700
Data Index: 1148354 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.1231. Min Act: -0.1700
Data Index: 1113291 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.0919. Min Act: -0.1700
Data Index: 4290313 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.0919. Min Act: -0.1700
Data Index: 3317916 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.0294. Min Act: -0.1700
Data Index: 5546520 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5294. Min Range: -8.5294
Max Act: 7.0294. Min Act: -0.1700
Data Index: 389397 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5294. Min Range: -8.5294
Max Act: 6.9981. Min Act: -0.1700
Data Index: 1172288 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5294. Min Range: -8.5294
Max Act: 6.9981. Min Act: -0.1700
Data Index: 5141035 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5294. Min Range: -8.5294
Max Act: 6.9981. Min Act: -0.1700
Data Index: 3465619 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #19