Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5283 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0935. Min Range: -8.0935
Max Act: 8.0935. Min Act: -0.1700
Data Index: 7693298 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.9685. Min Act: -0.1700
Data Index: 2423384 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.8435. Min Act: -0.1700
Data Index: 7830305 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.8435. Min Act: -0.1700
Data Index: 7706178 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.7185. Min Act: -0.1700
Data Index: 7501939 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.7185. Min Act: -0.1700
Data Index: 1721526 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.5622. Min Act: -0.1700
Data Index: 453099 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.5310. Min Act: -0.1700
Data Index: 5769989 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.4685. Min Act: -0.1700
Data Index: 166329 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.4685. Min Act: -0.1700
Data Index: 6487533 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.4997. Min Act: -0.1700
Data Index: 2976322 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.4372. Min Act: -0.1700
Data Index: 8219972 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.4372. Min Act: -0.1700
Data Index: 8659220 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.4685. Min Act: -0.1700
Data Index: 6098495 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.3747. Min Act: -0.1700
Data Index: 3867834 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.3747. Min Act: -0.1700
Data Index: 2524861 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.3122. Min Act: -0.1700
Data Index: 212550 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.3435. Min Act: -0.1700
Data Index: 3674847 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.3435. Min Act: -0.1700
Data Index: 2140544 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0935. Min Range: -8.0935
Max Act: 7.3122. Min Act: -0.1700
Data Index: 418286 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19