Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2800 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0874. Min Range: -6.0874
Max Act: 6.0874. Min Act: -0.1700
Data Index: 4405837 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.8374. Min Act: -0.1700
Data Index: 5085877 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.8062. Min Act: -0.1700
Data Index: 2524597 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.6812. Min Act: -0.1700
Data Index: 3510433 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.7124. Min Act: -0.1700
Data Index: 4057734 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.6499. Min Act: -0.1700
Data Index: 7671872 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.6187. Min Act: -0.1700
Data Index: 3598005 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.6187. Min Act: -0.1700
Data Index: 2454693 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.6187. Min Act: -0.1700
Data Index: 3576102 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.6187. Min Act: -0.1700
Data Index: 5529402 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.5874. Min Act: -0.1700
Data Index: 7814995 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.5874. Min Act: -0.1700
Data Index: 2801044 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.5562. Min Act: -0.1700
Data Index: 5197404 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.5562. Min Act: -0.1700
Data Index: 4974384 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.5562. Min Act: -0.1700
Data Index: 2305167 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.5562. Min Act: -0.1700
Data Index: 1987161 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.5249. Min Act: -0.1700
Data Index: 6603953 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.4937. Min Act: -0.1700
Data Index: 2857509 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.5249. Min Act: -0.1700
Data Index: 4232256 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0874. Min Range: -6.0874
Max Act: 5.4937. Min Act: -0.1700
Data Index: 1618027 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19