Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3408 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0810. Min Range: -5.0810
Max Act: 5.0810. Min Act: -0.1700
Data Index: 3392511 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0810. Min Range: -5.0810
Max Act: 5.0498. Min Act: -0.1700
Data Index: 4188530 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.9560. Min Act: -0.1700
Data Index: 1718747 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.9873. Min Act: -0.1700
Data Index: 8728379 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.9560. Min Act: -0.1700
Data Index: 1676277 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.9560. Min Act: -0.1700
Data Index: 4572197 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.9248. Min Act: -0.1700
Data Index: 1737722 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.9248. Min Act: -0.1700
Data Index: 2045664 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.8935. Min Act: -0.1700
Data Index: 4903489 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.8935. Min Act: -0.1700
Data Index: 7024078 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.8623. Min Act: -0.1700
Data Index: 2378650 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.8310. Min Act: -0.1700
Data Index: 2626588 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.8623. Min Act: -0.1700
Data Index: 5278976 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.8623. Min Act: -0.1700
Data Index: 7603810 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.8623. Min Act: -0.1700
Data Index: 6711150 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.8310. Min Act: -0.1700
Data Index: 4841577 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.8310. Min Act: -0.1700
Data Index: 6525121 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.8310. Min Act: -0.1700
Data Index: 6560378 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.8310. Min Act: -0.1700
Data Index: 4999857 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0810. Min Range: -5.0810
Max Act: 4.8310. Min Act: -0.1700
Data Index: 7386907 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19