Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2162 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5669. Min Range: -7.5669
Max Act: 7.5669. Min Act: -0.1700
Data Index: 2308333 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5669. Min Range: -7.5669
Max Act: 7.4732. Min Act: -0.1700
Data Index: 7705002 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5669. Min Range: -7.5669
Max Act: 7.3482. Min Act: -0.1700
Data Index: 2697630 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5669. Min Range: -7.5669
Max Act: 7.2232. Min Act: -0.1700
Data Index: 6446877 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5669. Min Range: -7.5669
Max Act: 7.1919. Min Act: -0.1700
Data Index: 7529467 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5669. Min Range: -7.5669
Max Act: 7.0982. Min Act: -0.1700
Data Index: 2129582 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5669. Min Range: -7.5669
Max Act: 7.0357. Min Act: -0.1700
Data Index: 6991902 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5669. Min Range: -7.5669
Max Act: 7.0044. Min Act: -0.1700
Data Index: 1862423 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5669. Min Range: -7.5669
Max Act: 6.9732. Min Act: -0.1700
Data Index: 4590617 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5669. Min Range: -7.5669
Max Act: 6.9107. Min Act: -0.1700
Data Index: 8373582 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5669. Min Range: -7.5669
Max Act: 6.9732. Min Act: -0.1700
Data Index: 603498 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5669. Min Range: -7.5669
Max Act: 6.9107. Min Act: -0.1700
Data Index: 3280438 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5669. Min Range: -7.5669
Max Act: 6.9107. Min Act: -0.1700
Data Index: 1570312 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5669. Min Range: -7.5669
Max Act: 6.9107. Min Act: -0.1700
Data Index: 4454957 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5669. Min Range: -7.5669
Max Act: 6.8794. Min Act: -0.1700
Data Index: 1586995 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5669. Min Range: -7.5669
Max Act: 6.9107. Min Act: -0.1700
Data Index: 4827592 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5669. Min Range: -7.5669
Max Act: 6.8169. Min Act: -0.1700
Data Index: 1772089 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5669. Min Range: -7.5669
Max Act: 6.8169. Min Act: -0.1700
Data Index: 871174 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5669. Min Range: -7.5669
Max Act: 6.8482. Min Act: -0.1700
Data Index: 3602418 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5669. Min Range: -7.5669
Max Act: 6.8169. Min Act: -0.1700
Data Index: 4727920 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19