Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.8217. Min Act: -0.1700
Data Index: 4048917 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.8217. Min Act: -0.1700
Data Index: 8189306 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.8217. Min Act: -0.1700
Data Index: 6160671 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.7592. Min Act: -0.1700
Data Index: 4306788 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.7280. Min Act: -0.1700
Data Index: 7971184 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.7280. Min Act: -0.1700
Data Index: 5098390 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.6967. Min Act: -0.1700
Data Index: 3389040 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.6342. Min Act: -0.1700
Data Index: 5376581 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.6654. Min Act: -0.1700
Data Index: 3349421 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.6654. Min Act: -0.1700
Data Index: 1809287 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.6654. Min Act: -0.1700
Data Index: 7602553 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.6342. Min Act: -0.1700
Data Index: 522566 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.6342. Min Act: -0.1700
Data Index: 140042 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.6342. Min Act: -0.1700
Data Index: 4342066 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.6029. Min Act: -0.1700
Data Index: 1549290 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.5717. Min Act: -0.1700
Data Index: 5421031 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.5717. Min Act: -0.1700
Data Index: 6095605 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.5717. Min Act: -0.1700
Data Index: 8357986 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.5717. Min Act: -0.1700
Data Index: 5283383 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8217. Min Range: -4.8217
Max Act: 4.5092. Min Act: -0.1700
Data Index: 7101126 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19