Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3467 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.6310. Min Act: -0.1700
Data Index: 1997945 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.6310. Min Act: -0.1700
Data Index: 4729777 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.6310. Min Act: -0.1700
Data Index: 7741878 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.5998. Min Act: -0.1700
Data Index: 7001241 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.6310. Min Act: -0.1700
Data Index: 590645 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.5998. Min Act: -0.1700
Data Index: 414638 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.5685. Min Act: -0.1700
Data Index: 3654296 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.5685. Min Act: -0.1700
Data Index: 1415369 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.5373. Min Act: -0.1700
Data Index: 6451415 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.5060. Min Act: -0.1700
Data Index: 2850096 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.4435. Min Act: -0.1700
Data Index: 712783 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.4748. Min Act: -0.1700
Data Index: 4805666 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.4748. Min Act: -0.1700
Data Index: 3829709 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.4435. Min Act: -0.1700
Data Index: 3835746 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.4435. Min Act: -0.1700
Data Index: 278156 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.4435. Min Act: -0.1700
Data Index: 4354174 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.4435. Min Act: -0.1700
Data Index: 5573104 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.4435. Min Act: -0.1700
Data Index: 1013653 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.4435. Min Act: -0.1700
Data Index: 6182390 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6310. Min Range: -6.6310
Max Act: 6.4123. Min Act: -0.1700
Data Index: 4391957 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19