Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 919 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.8132. Min Act: -0.1700
Data Index: 2562861 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.8132. Min Act: -0.1700
Data Index: 4665924 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.7194. Min Act: -0.1700
Data Index: 2639037 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.7194. Min Act: -0.1700
Data Index: 5525372 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.6882. Min Act: -0.1700
Data Index: 1903878 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.6882. Min Act: -0.1700
Data Index: 4863126 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5944. Min Act: -0.1700
Data Index: 5915059 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5632. Min Act: -0.1700
Data Index: 8805612 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5944. Min Act: -0.1700
Data Index: 8141064 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5944. Min Act: -0.1700
Data Index: 5669492 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5944. Min Act: -0.1700
Data Index: 4665926 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5944. Min Act: -0.1700
Data Index: 3445885 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5632. Min Act: -0.1700
Data Index: 5528100 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5632. Min Act: -0.1700
Data Index: 2850705 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5632. Min Act: -0.1700
Data Index: 494681 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5632. Min Act: -0.1700
Data Index: 3293666 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5319. Min Act: -0.1700
Data Index: 610978 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5319. Min Act: -0.1700
Data Index: 4626731 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5319. Min Act: -0.1700
Data Index: 7079977 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8132. Min Range: -6.8132
Max Act: 6.5319. Min Act: -0.1700
Data Index: 2129662 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #19