Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6071 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0713. Min Range: -8.0713
Max Act: 8.0713. Min Act: -0.1700
Data Index: 390903 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0713. Min Range: -8.0713
Max Act: 8.0088. Min Act: -0.1700
Data Index: 4795782 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.8838. Min Act: -0.1700
Data Index: 8259452 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.8526. Min Act: -0.1700
Data Index: 6934646 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.8213. Min Act: -0.1700
Data Index: 7788425 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.8526. Min Act: -0.1700
Data Index: 472413 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.8213. Min Act: -0.1700
Data Index: 2559754 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.7588. Min Act: -0.1700
Data Index: 1567615 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.7901. Min Act: -0.1700
Data Index: 8756569 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.7588. Min Act: -0.1700
Data Index: 994669 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.7588. Min Act: -0.1700
Data Index: 3159821 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.7588. Min Act: -0.1700
Data Index: 7391807 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.7276. Min Act: -0.1700
Data Index: 8477156 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.7276. Min Act: -0.1700
Data Index: 4118911 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.7588. Min Act: -0.1700
Data Index: 4006992 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.6963. Min Act: -0.1700
Data Index: 5598273 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.7276. Min Act: -0.1700
Data Index: 1684528 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.6651. Min Act: -0.1700
Data Index: 636657 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.6963. Min Act: -0.1700
Data Index: 4667231 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0713. Min Range: -8.0713
Max Act: 7.6026. Min Act: -0.1700
Data Index: 8045930 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19