Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3848 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.5590. Min Act: -0.1700
Data Index: 7160221 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.5277. Min Act: -0.1700
Data Index: 7129525 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.4652. Min Act: -0.1700
Data Index: 2210418 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.4340. Min Act: -0.1700
Data Index: 957662 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.4340. Min Act: -0.1700
Data Index: 5564625 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.3402. Min Act: -0.1700
Data Index: 201851 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.3402. Min Act: -0.1700
Data Index: 4098562 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.3402. Min Act: -0.1700
Data Index: 7347958 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.3090. Min Act: -0.1700
Data Index: 4564407 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.2465. Min Act: -0.1700
Data Index: 5451365 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.2152. Min Act: -0.1700
Data Index: 2845148 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.2152. Min Act: -0.1700
Data Index: 1827932 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.0902. Min Act: -0.1700
Data Index: 1509008 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.0902. Min Act: -0.1700
Data Index: 6290489 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.0902. Min Act: -0.1700
Data Index: 5621948 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.0902. Min Act: -0.1700
Data Index: 4568519 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5590. Min Range: -6.5590
Max Act: 6.0277. Min Act: -0.1700
Data Index: 4091843 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5590. Min Range: -6.5590
Max Act: 5.9965. Min Act: -0.1700
Data Index: 5163250 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5590. Min Range: -6.5590
Max Act: 5.9652. Min Act: -0.1700
Data Index: 2074089 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5590. Min Range: -6.5590
Max Act: 5.9340. Min Act: -0.1700
Data Index: 405072 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19