Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4678 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.4780. Min Act: -0.1700
Data Index: 1309821 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.4155. Min Act: -0.1700
Data Index: 7074300 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.4155. Min Act: -0.1700
Data Index: 193459 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.4155. Min Act: -0.1700
Data Index: 7706280 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.3843. Min Act: -0.1700
Data Index: 5741247 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.3530. Min Act: -0.1700
Data Index: 4967714 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.2905. Min Act: -0.1700
Data Index: 4693230 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.2905. Min Act: -0.1700
Data Index: 22282 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.2905. Min Act: -0.1700
Data Index: 7525716 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.2593. Min Act: -0.1700
Data Index: 5969418 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.2280. Min Act: -0.1700
Data Index: 1373521 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.2280. Min Act: -0.1700
Data Index: 5874777 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.1968. Min Act: -0.1700
Data Index: 2784183 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.1968. Min Act: -0.1700
Data Index: 124341 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.1655. Min Act: -0.1700
Data Index: 5821417 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.1655. Min Act: -0.1700
Data Index: 7552667 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.1655. Min Act: -0.1700
Data Index: 4437761 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.1655. Min Act: -0.1700
Data Index: 6127449 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.1655. Min Act: -0.1700
Data Index: 2375021 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4780. Min Range: -6.4780
Max Act: 6.1655. Min Act: -0.1700
Data Index: 4581173 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19