Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5299 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.8176. Min Act: -0.1700
Data Index: 4073752 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.8489. Min Act: -0.1700
Data Index: 6179503 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.7864. Min Act: -0.1700
Data Index: 8328473 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.7864. Min Act: -0.1700
Data Index: 8386237 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.7864. Min Act: -0.1700
Data Index: 1203987 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.7551. Min Act: -0.1700
Data Index: 674586 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.7551. Min Act: -0.1700
Data Index: 7605188 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.7238. Min Act: -0.1700
Data Index: 2652235 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.6925. Min Act: -0.1700
Data Index: 8476560 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.6925. Min Act: -0.1700
Data Index: 1496116 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.6925. Min Act: -0.1700
Data Index: 3835239 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.6612. Min Act: -0.1700
Data Index: 6849073 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.6612. Min Act: -0.1700
Data Index: 5374382 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.6612. Min Act: -0.1700
Data Index: 8309225 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.6612. Min Act: -0.1700
Data Index: 1513928 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.6612. Min Act: -0.1700
Data Index: 5762226 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.6612. Min Act: -0.1700
Data Index: 1735065 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.6612. Min Act: -0.1700
Data Index: 5458002 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.6299. Min Act: -0.1700
Data Index: 8291354 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8489. Min Range: -3.8489
Max Act: 3.6299. Min Act: -0.1700
Data Index: 5929365 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19