Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 622 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0485. Min Range: -7.0485
Max Act: 7.0485. Min Act: -0.1700
Data Index: 1987702 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.9860. Min Act: -0.1700
Data Index: 8287668 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.9860. Min Act: -0.1700
Data Index: 2141524 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.8922. Min Act: -0.1700
Data Index: 5832996 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.8610. Min Act: -0.1700
Data Index: 7808901 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.8297. Min Act: -0.1700
Data Index: 7224343 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.8297. Min Act: -0.1700
Data Index: 594193 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.7985. Min Act: -0.1700
Data Index: 6905474 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.7360. Min Act: -0.1700
Data Index: 7982564 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.7672. Min Act: -0.1700
Data Index: 7134618 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.7360. Min Act: -0.1700
Data Index: 6466475 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.7047. Min Act: -0.1700
Data Index: 467291 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.7047. Min Act: -0.1700
Data Index: 7767111 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.7047. Min Act: -0.1700
Data Index: 4046232 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.6735. Min Act: -0.1700
Data Index: 3223110 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.6735. Min Act: -0.1700
Data Index: 4810321 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.6110. Min Act: -0.1700
Data Index: 1709417 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.6110. Min Act: -0.1700
Data Index: 3936825 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.6110. Min Act: -0.1700
Data Index: 4081177 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0485. Min Range: -7.0485
Max Act: 6.6110. Min Act: -0.1700
Data Index: 3187230 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19