Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1249 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.8318. Min Act: -0.1700
Data Index: 633384 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.7068. Min Act: -0.1700
Data Index: 1383072 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.6755. Min Act: -0.1700
Data Index: 5837753 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.6755. Min Act: -0.1700
Data Index: 3397811 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.6130. Min Act: -0.1700
Data Index: 8815386 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.6130. Min Act: -0.1700
Data Index: 8463207 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.6130. Min Act: -0.1700
Data Index: 8815384 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.6130. Min Act: -0.1700
Data Index: 1149171 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.5818. Min Act: -0.1700
Data Index: 8557601 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.5818. Min Act: -0.1700
Data Index: 7498930 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.5818. Min Act: -0.1700
Data Index: 5650011 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.5193. Min Act: -0.1700
Data Index: 7740000 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.5505. Min Act: -0.1700
Data Index: 7422082 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.5505. Min Act: -0.1700
Data Index: 6373640 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.5505. Min Act: -0.1700
Data Index: 6924186 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.5505. Min Act: -0.1700
Data Index: 3684826 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.5193. Min Act: -0.1700
Data Index: 4369048 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.5193. Min Act: -0.1700
Data Index: 4665029 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.5193. Min Act: -0.1700
Data Index: 3555499 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8318. Min Range: -4.8318
Max Act: 4.4880. Min Act: -0.1700
Data Index: 5137189 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19