Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 186 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1769. Min Range: -2.1769
Max Act: 2.1769. Min Act: -0.1700
Data Index: 5448824 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1769. Min Range: -2.1769
Max Act: 2.1436. Min Act: -0.1700
Data Index: 7277779 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1769. Min Range: -2.1769
Max Act: 2.0934. Min Act: -0.1700
Data Index: 6927255 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1769. Min Range: -2.1769
Max Act: 2.0934. Min Act: -0.1700
Data Index: 8697926 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1769. Min Range: -2.1769
Max Act: 2.0599. Min Act: -0.1700
Data Index: 2976530 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1769. Min Range: -2.1769
Max Act: 2.0430. Min Act: -0.1700
Data Index: 6244576 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1769. Min Range: -2.1769
Max Act: 2.0093. Min Act: -0.1700
Data Index: 6722373 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1769. Min Range: -2.1769
Max Act: 2.0093. Min Act: -0.1700
Data Index: 4049154 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1769. Min Range: -2.1769
Max Act: 2.0093. Min Act: -0.1700
Data Index: 2563647 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1769. Min Range: -2.1769
Max Act: 1.9924. Min Act: -0.1700
Data Index: 5572893 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1769. Min Range: -2.1769
Max Act: 1.9924. Min Act: -0.1700
Data Index: 2920762 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1769. Min Range: -2.1769
Max Act: 1.9755. Min Act: -0.1700
Data Index: 1312518 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1769. Min Range: -2.1769
Max Act: 1.9755. Min Act: -0.1700
Data Index: 7145110 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1769. Min Range: -2.1769
Max Act: 1.9416. Min Act: -0.1700
Data Index: 2905030 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1769. Min Range: -2.1769
Max Act: 1.9416. Min Act: -0.1700
Data Index: 2077397 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1769. Min Range: -2.1769
Max Act: 1.9755. Min Act: -0.1700
Data Index: 387727 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1769. Min Range: -2.1769
Max Act: 1.9416. Min Act: -0.1700
Data Index: 553293 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1769. Min Range: -2.1769
Max Act: 1.9586. Min Act: -0.1700
Data Index: 5651194 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1769. Min Range: -2.1769
Max Act: 1.9416. Min Act: -0.1700
Data Index: 6538127 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1769. Min Range: -2.1769
Max Act: 1.9416. Min Act: -0.1700
Data Index: 2065616 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19