Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3498 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.2009. Min Act: -0.1700
Data Index: 4694707 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.2009. Min Act: -0.1700
Data Index: 780523 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.1851. Min Act: -0.1700
Data Index: 6887468 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.1064. Min Act: -0.1700
Data Index: 8730273 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.1222. Min Act: -0.1700
Data Index: 6724052 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0907. Min Act: -0.1700
Data Index: 4008121 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.1064. Min Act: -0.1700
Data Index: 4526412 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0749. Min Act: -0.1700
Data Index: 3017394 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0591. Min Act: -0.1700
Data Index: 2491476 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0749. Min Act: -0.1700
Data Index: 3050939 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0749. Min Act: -0.1700
Data Index: 5060118 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0749. Min Act: -0.1700
Data Index: 7718775 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0433. Min Act: -0.1700
Data Index: 5149945 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0276. Min Act: -0.1700
Data Index: 85436 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0276. Min Act: -0.1700
Data Index: 358164 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0118. Min Act: -0.1700
Data Index: 4427667 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2009. Min Range: -3.2009
Max Act: 3.0276. Min Act: -0.1700
Data Index: 1576699 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9960. Min Act: -0.1700
Data Index: 2886841 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9960. Min Act: -0.1700
Data Index: 3727119 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2009. Min Range: -3.2009
Max Act: 2.9801. Min Act: -0.1700
Data Index: 584825 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19