Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3242 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.8735. Min Act: -0.1700
Data Index: 7284126 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.8110. Min Act: -0.1700
Data Index: 895919 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.8110. Min Act: -0.1700
Data Index: 2977012 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.7797. Min Act: -0.1700
Data Index: 2093248 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.7485. Min Act: -0.1700
Data Index: 2138380 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.7172. Min Act: -0.1700
Data Index: 2030621 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.6860. Min Act: -0.1700
Data Index: 6260581 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.5610. Min Act: -0.1700
Data Index: 2092347 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.5922. Min Act: -0.1700
Data Index: 6269749 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.5610. Min Act: -0.1700
Data Index: 1921319 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.5297. Min Act: -0.1700
Data Index: 1940092 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.4985. Min Act: -0.1700
Data Index: 6848265 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.4360. Min Act: -0.1700
Data Index: 403820 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.4360. Min Act: -0.1700
Data Index: 8500269 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.4360. Min Act: -0.1700
Data Index: 1445317 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.4360. Min Act: -0.1700
Data Index: 6745082 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.4047. Min Act: -0.1700
Data Index: 67585 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.4047. Min Act: -0.1700
Data Index: 6239999 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.4047. Min Act: -0.1700
Data Index: 1684154 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8735. Min Range: -5.8735
Max Act: 5.3422. Min Act: -0.1700
Data Index: 6625518 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19