Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1955 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.6098. Min Act: -0.1700
Data Index: 958074 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.5160. Min Act: -0.1700
Data Index: 3045929 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.4223. Min Act: -0.1700
Data Index: 31446 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.3598. Min Act: -0.1700
Data Index: 5846625 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.3285. Min Act: -0.1700
Data Index: 8787119 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.2660. Min Act: -0.1700
Data Index: 5382839 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.2660. Min Act: -0.1700
Data Index: 6295861 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.2660. Min Act: -0.1700
Data Index: 1620000 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.2348. Min Act: -0.1700
Data Index: 965301 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.2348. Min Act: -0.1700
Data Index: 3587799 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.2348. Min Act: -0.1700
Data Index: 1907281 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.2035. Min Act: -0.1700
Data Index: 951592 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.2348. Min Act: -0.1700
Data Index: 5992973 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.1723. Min Act: -0.1700
Data Index: 7565076 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.1723. Min Act: -0.1700
Data Index: 953217 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.1723. Min Act: -0.1700
Data Index: 1062469 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.1723. Min Act: -0.1700
Data Index: 8520019 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.1723. Min Act: -0.1700
Data Index: 1931206 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.1098. Min Act: -0.1700
Data Index: 1353768 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6098. Min Range: -5.6098
Max Act: 5.1410. Min Act: -0.1700
Data Index: 739595 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #19