Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3090. Min Range: -5.3090
Max Act: 5.3090. Min Act: -0.1700
Data Index: 2983433 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3090. Min Range: -5.3090
Max Act: 5.2465. Min Act: -0.1700
Data Index: 7198898 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3090. Min Range: -5.3090
Max Act: 5.1528. Min Act: -0.1700
Data Index: 8208750 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3090. Min Range: -5.3090
Max Act: 5.0278. Min Act: -0.1700
Data Index: 2187379 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9965. Min Act: -0.1700
Data Index: 2903144 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9965. Min Act: -0.1700
Data Index: 1950186 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9965. Min Act: -0.1700
Data Index: 4681807 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9965. Min Act: -0.1700
Data Index: 6285157 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9340. Min Act: -0.1700
Data Index: 2639814 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9653. Min Act: -0.1700
Data Index: 7162263 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9653. Min Act: -0.1700
Data Index: 5757006 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9965. Min Act: -0.1700
Data Index: 6694979 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9653. Min Act: -0.1700
Data Index: 7357136 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9653. Min Act: -0.1700
Data Index: 1983592 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9653. Min Act: -0.1700
Data Index: 2907257 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9653. Min Act: -0.1700
Data Index: 8377305 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9340. Min Act: -0.1700
Data Index: 5623085 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9340. Min Act: -0.1700
Data Index: 2538440 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9028. Min Act: -0.1700
Data Index: 968120 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3090. Min Range: -5.3090
Max Act: 4.9340. Min Act: -0.1700
Data Index: 8113325 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19