Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7237. Min Range: -8.7237
Max Act: 8.7237. Min Act: -0.1700
Data Index: 6687994 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7237. Min Range: -8.7237
Max Act: 8.6612. Min Act: -0.1700
Data Index: 1836476 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7237. Min Range: -8.7237
Max Act: 8.2237. Min Act: -0.1700
Data Index: 7074016 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.9737. Min Act: -0.1700
Data Index: 3759934 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7237. Min Range: -8.7237
Max Act: 8.0050. Min Act: -0.1700
Data Index: 3533139 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.9425. Min Act: -0.1700
Data Index: 5245902 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.7862. Min Act: -0.1700
Data Index: 6080408 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.7237. Min Act: -0.1700
Data Index: 7074012 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.6925. Min Act: -0.1700
Data Index: 7074014 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.6300. Min Act: -0.1700
Data Index: 7074011 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.6300. Min Act: -0.1700
Data Index: 7074018 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.5987. Min Act: -0.1700
Data Index: 7074013 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.5987. Min Act: -0.1700
Data Index: 3071424 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.5362. Min Act: -0.1700
Data Index: 641181 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.5050. Min Act: -0.1700
Data Index: 7074019 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.3800. Min Act: -0.1700
Data Index: 641180 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.3800. Min Act: -0.1700
Data Index: 7348209 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.3487. Min Act: -0.1700
Data Index: 7690804 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.3800. Min Act: -0.1700
Data Index: 5446802 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7237. Min Range: -8.7237
Max Act: 7.3487. Min Act: -0.1700
Data Index: 16743 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19