Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 392 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 5.2957. Min Range: -5.2957
Max Act: 5.2957. Min Act: -0.1700
Data Index: 4506472 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2957. Min Range: -5.2957
Max Act: 5.1082. Min Act: -0.1700
Data Index: 1516281 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2957. Min Range: -5.2957
Max Act: 5.1394. Min Act: -0.1700
Data Index: 6345320 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2957. Min Range: -5.2957
Max Act: 5.0769. Min Act: -0.1700
Data Index: 3004018 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2957. Min Range: -5.2957
Max Act: 5.0144. Min Act: -0.1700
Data Index: 5399550 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2957. Min Range: -5.2957
Max Act: 5.0769. Min Act: -0.1700
Data Index: 8279012 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2957. Min Range: -5.2957
Max Act: 4.9832. Min Act: -0.1700
Data Index: 4979330 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2957. Min Range: -5.2957
Max Act: 4.9832. Min Act: -0.1700
Data Index: 2329281 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2957. Min Range: -5.2957
Max Act: 4.9519. Min Act: -0.1700
Data Index: 1732455 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2957. Min Range: -5.2957
Max Act: 4.9832. Min Act: -0.1700
Data Index: 59129 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2957. Min Range: -5.2957
Max Act: 5.0144. Min Act: -0.1700
Data Index: 3145902 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2957. Min Range: -5.2957
Max Act: 4.9519. Min Act: -0.1700
Data Index: 4705166 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2957. Min Range: -5.2957
Max Act: 4.9519. Min Act: -0.1700
Data Index: 4140434 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2957. Min Range: -5.2957
Max Act: 5.0144. Min Act: -0.1700
Data Index: 3591812 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2957. Min Range: -5.2957
Max Act: 4.9519. Min Act: -0.1700
Data Index: 638551 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2957. Min Range: -5.2957
Max Act: 4.9832. Min Act: -0.1700
Data Index: 367079 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2957. Min Range: -5.2957
Max Act: 4.9519. Min Act: -0.1700
Data Index: 5684948 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2957. Min Range: -5.2957
Max Act: 4.9519. Min Act: -0.1700
Data Index: 114429 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2957. Min Range: -5.2957
Max Act: 4.9519. Min Act: -0.1700
Data Index: 4306165 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2957. Min Range: -5.2957
Max Act: 4.9832. Min Act: -0.1700
Data Index: 666613 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19