Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3261 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.6797. Min Act: -0.1700
Data Index: 2319643 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.6485. Min Act: -0.1700
Data Index: 1987754 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.5547. Min Act: -0.1700
Data Index: 2227044 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.5235. Min Act: -0.1700
Data Index: 805967 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.5235. Min Act: -0.1700
Data Index: 1704262 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.5547. Min Act: -0.1700
Data Index: 6061683 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.4922. Min Act: -0.1700
Data Index: 7324890 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.4922. Min Act: -0.1700
Data Index: 5592856 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.5235. Min Act: -0.1700
Data Index: 269361 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.4610. Min Act: -0.1700
Data Index: 7348587 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.4610. Min Act: -0.1700
Data Index: 3808436 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.4610. Min Act: -0.1700
Data Index: 1985786 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.4297. Min Act: -0.1700
Data Index: 838446 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.3985. Min Act: -0.1700
Data Index: 4749331 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.3985. Min Act: -0.1700
Data Index: 4310500 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.3985. Min Act: -0.1700
Data Index: 6323848 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.3985. Min Act: -0.1700
Data Index: 6514969 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.3985. Min Act: -0.1700
Data Index: 5643943 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.3985. Min Act: -0.1699
Data Index: 5466238 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6797. Min Range: -6.6797
Max Act: 6.3985. Min Act: -0.1700
Data Index: 5592769 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19