Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2997 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.6033. Min Act: -0.1700
Data Index: 4512875 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.5096. Min Act: -0.1700
Data Index: 2928958 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.5096. Min Act: -0.1700
Data Index: 214282 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.3533. Min Act: -0.1700
Data Index: 840757 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.3533. Min Act: -0.1700
Data Index: 716591 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.3221. Min Act: -0.1700
Data Index: 4336705 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.2908. Min Act: -0.1700
Data Index: 6872458 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.2596. Min Act: -0.1700
Data Index: 3701962 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.2283. Min Act: -0.1700
Data Index: 8035988 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.2596. Min Act: -0.1700
Data Index: 6976231 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.1970. Min Act: -0.1700
Data Index: 4717772 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.1970. Min Act: -0.1700
Data Index: 3343247 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.1970. Min Act: -0.1700
Data Index: 3979922 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.2283. Min Act: -0.1700
Data Index: 7492346 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.1970. Min Act: -0.1700
Data Index: 4577837 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.1970. Min Act: -0.1700
Data Index: 8712690 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.1970. Min Act: -0.1700
Data Index: 5228221 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.1658. Min Act: -0.1700
Data Index: 8576142 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.1658. Min Act: -0.1700
Data Index: 759888 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6033. Min Range: -4.6033
Max Act: 4.1658. Min Act: -0.1700
Data Index: 8665172 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #19