Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2733 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1207. Min Range: -8.1207
Max Act: 8.1207. Min Act: -0.1700
Data Index: 860938 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1207. Min Range: -8.1207
Max Act: 8.1207. Min Act: -0.1700
Data Index: 1135320 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.9332. Min Act: -0.1700
Data Index: 169297 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.9332. Min Act: -0.1700
Data Index: 1202465 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.9332. Min Act: -0.1700
Data Index: 8194892 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.8707. Min Act: -0.1700
Data Index: 2857826 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.8707. Min Act: -0.1700
Data Index: 2461879 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.8707. Min Act: -0.1700
Data Index: 1281733 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.8082. Min Act: -0.1700
Data Index: 104479 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.8082. Min Act: -0.1700
Data Index: 8027407 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.8082. Min Act: -0.1699
Data Index: 1543316 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.7457. Min Act: -0.1700
Data Index: 1261352 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.7457. Min Act: -0.1700
Data Index: 5878639 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.7457. Min Act: -0.1700
Data Index: 5976872 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.7457. Min Act: -0.1700
Data Index: 7941281 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.7457. Min Act: -0.1700
Data Index: 7970525 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.7457. Min Act: -0.1700
Data Index: 2262039 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.7457. Min Act: -0.1687
Data Index: 2759160 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.7457. Min Act: -0.1700
Data Index: 1848721 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1207. Min Range: -8.1207
Max Act: 7.7457. Min Act: -0.1700
Data Index: 1725946 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #19