Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1091 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4948. Min Range: -8.4948
Max Act: 8.4948. Min Act: -0.1700
Data Index: 4517865 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4948. Min Range: -8.4948
Max Act: 8.3698. Min Act: -0.1700
Data Index: 2268409 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4948. Min Range: -8.4948
Max Act: 8.1823. Min Act: -0.1700
Data Index: 1886833 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4948. Min Range: -8.4948
Max Act: 8.1198. Min Act: -0.1700
Data Index: 5124000 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4948. Min Range: -8.4948
Max Act: 8.1198. Min Act: -0.1700
Data Index: 2772062 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.9948. Min Act: -0.1700
Data Index: 5872720 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.9323. Min Act: -0.1700
Data Index: 8495792 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.9323. Min Act: -0.1700
Data Index: 2710329 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.9323. Min Act: -0.1700
Data Index: 7690500 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.8698. Min Act: -0.1700
Data Index: 835885 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.8698. Min Act: -0.1700
Data Index: 6047516 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.8698. Min Act: -0.1700
Data Index: 4943625 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.8698. Min Act: -0.1700
Data Index: 2132414 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.8698. Min Act: -0.1700
Data Index: 7160746 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.8073. Min Act: -0.1700
Data Index: 4226662 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.7760. Min Act: -0.1700
Data Index: 7953026 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.7448. Min Act: -0.1700
Data Index: 1558268 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.7448. Min Act: -0.1700
Data Index: 1499735 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.6823. Min Act: -0.1700
Data Index: 4198685 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4948. Min Range: -8.4948
Max Act: 7.6823. Min Act: -0.1700
Data Index: 4072113 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #19