Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3089 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.9194. Min Act: -0.1700
Data Index: 8168475 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.9819. Min Act: -0.1700
Data Index: 1923089 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.9194. Min Act: -0.1700
Data Index: 2187884 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.9194. Min Act: -0.1700
Data Index: 778985 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.9194. Min Act: -0.1700
Data Index: 4124029 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8882. Min Act: -0.1700
Data Index: 7914225 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8882. Min Act: -0.1700
Data Index: 1414481 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8882. Min Act: -0.1700
Data Index: 5107053 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8882. Min Act: -0.1700
Data Index: 4494942 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8882. Min Act: -0.1700
Data Index: 7127228 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8882. Min Act: -0.1700
Data Index: 6657449 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8882. Min Act: -0.1700
Data Index: 7356702 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8569. Min Act: -0.1700
Data Index: 4389579 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8569. Min Act: -0.1700
Data Index: 2721387 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8569. Min Act: -0.1700
Data Index: 3201966 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8569. Min Act: -0.1700
Data Index: 7314282 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8569. Min Act: -0.1700
Data Index: 6250161 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8569. Min Act: -0.1700
Data Index: 4066310 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8569. Min Act: -0.1700
Data Index: 2274673 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9819. Min Range: -4.9819
Max Act: 4.8569. Min Act: -0.1700
Data Index: 4082605 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19