Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2812 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2344. Min Range: -9.2344
Max Act: 9.2344. Min Act: -0.1700
Data Index: 8448181 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.5469. Min Act: -0.1700
Data Index: 4292163 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.4844. Min Act: -0.1700
Data Index: 2921830 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.4844. Min Act: -0.1700
Data Index: 3162923 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.4219. Min Act: -0.1700
Data Index: 6520521 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.4844. Min Act: -0.1700
Data Index: 5879660 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.3594. Min Act: -0.1700
Data Index: 8371378 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.2969. Min Act: -0.1700
Data Index: 8100537 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.2969. Min Act: -0.1700
Data Index: 796306 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.1719. Min Act: -0.1700
Data Index: 6706479 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.1407. Min Act: -0.1700
Data Index: 7336620 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.1719. Min Act: -0.1700
Data Index: 6216153 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.1094. Min Act: -0.1700
Data Index: 7368904 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.0469. Min Act: -0.1700
Data Index: 1877732 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.0782. Min Act: -0.1700
Data Index: 457938 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.0469. Min Act: -0.1700
Data Index: 8474160 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.0469. Min Act: -0.1700
Data Index: 4338264 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.0157. Min Act: -0.1700
Data Index: 7699218 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2344. Min Range: -9.2344
Max Act: 7.9844. Min Act: -0.1700
Data Index: 5443000 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2344. Min Range: -9.2344
Max Act: 8.0157. Min Act: -0.1700
Data Index: 4248577 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19