Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3815 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6935. Min Act: -0.1700
Data Index: 4535179 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6622. Min Act: -0.1700
Data Index: 4644851 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6622. Min Act: -0.1700
Data Index: 476893 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6622. Min Act: -0.1700
Data Index: 8656823 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6622. Min Act: -0.1700
Data Index: 7646340 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6309. Min Act: -0.1700
Data Index: 2964108 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6309. Min Act: -0.1700
Data Index: 8461214 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6309. Min Act: -0.1700
Data Index: 6366449 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5996. Min Act: -0.1700
Data Index: 5224879 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6309. Min Act: -0.1700
Data Index: 1844952 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.6309. Min Act: -0.1700
Data Index: 637834 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5996. Min Act: -0.1700
Data Index: 3265914 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5996. Min Act: -0.1700
Data Index: 7654088 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5683. Min Act: -0.1700
Data Index: 637831 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5996. Min Act: -0.1700
Data Index: 1649464 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5996. Min Act: -0.1700
Data Index: 4671187 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5996. Min Act: -0.1700
Data Index: 8820906 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5996. Min Act: -0.1700
Data Index: 1910511 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5683. Min Act: -0.1700
Data Index: 5045021 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6935. Min Range: -3.6935
Max Act: 3.5683. Min Act: -0.1700
Data Index: 50478 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #19