Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2682 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.8530. Min Act: -0.1700
Data Index: 7160378 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.8530. Min Act: -0.1700
Data Index: 6701867 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.8530. Min Act: -0.1700
Data Index: 442047 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.8217. Min Act: -0.1700
Data Index: 3001718 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.6030. Min Act: -0.1700
Data Index: 3394730 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.5717. Min Act: -0.1700
Data Index: 8460679 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.5405. Min Act: -0.1700
Data Index: 4549353 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.5092. Min Act: -0.1700
Data Index: 6322673 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.4780. Min Act: -0.1700
Data Index: 129391 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.4467. Min Act: -0.1700
Data Index: 255663 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.4780. Min Act: -0.1700
Data Index: 1421966 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.4780. Min Act: -0.1700
Data Index: 579447 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.5092. Min Act: -0.1700
Data Index: 1648609 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.4155. Min Act: -0.1700
Data Index: 3966735 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.4155. Min Act: -0.1700
Data Index: 503033 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.4467. Min Act: -0.1700
Data Index: 1536121 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.4155. Min Act: -0.1700
Data Index: 1253748 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.3842. Min Act: -0.1700
Data Index: 1233087 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.4155. Min Act: -0.1700
Data Index: 1079970 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8530. Min Range: -6.8530
Max Act: 6.3842. Min Act: -0.1700
Data Index: 2536143 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19