Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2280 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.6595. Min Act: -0.1700
Data Index: 645837 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5953. Min Act: -0.1700
Data Index: 7375908 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5953. Min Act: -0.1700
Data Index: 8580398 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5792. Min Act: -0.1700
Data Index: 8282747 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5953. Min Act: -0.1700
Data Index: 4422650 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5953. Min Act: -0.1700
Data Index: 6768828 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 5055263 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 1431452 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 569005 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 6838952 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 97693 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 3546021 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 2894948 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 6891541 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5630. Min Act: -0.1700
Data Index: 2192679 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 6789687 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 6957938 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 1299170 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 1215762 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6595. Min Range: -2.6595
Max Act: 2.5469. Min Act: -0.1700
Data Index: 6221463 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19