Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4304 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4095. Min Range: -6.4095
Max Act: 6.4095. Min Act: -0.1700
Data Index: 7440463 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.9720. Min Act: -0.1700
Data Index: 1071897 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.9408. Min Act: -0.1700
Data Index: 8197424 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.9095. Min Act: -0.1700
Data Index: 4792518 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.8470. Min Act: -0.1700
Data Index: 413116 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.8158. Min Act: -0.1700
Data Index: 4915817 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.7845. Min Act: -0.1700
Data Index: 6882758 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.7220. Min Act: -0.1700
Data Index: 7487040 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.6908. Min Act: -0.1700
Data Index: 6916092 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.6595. Min Act: -0.1700
Data Index: 5693853 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.6595. Min Act: -0.1700
Data Index: 7077420 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.6283. Min Act: -0.1700
Data Index: 2655122 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.5970. Min Act: -0.1700
Data Index: 5272204 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.6283. Min Act: -0.1700
Data Index: 8133884 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.6283. Min Act: -0.1700
Data Index: 6356001 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.6283. Min Act: -0.1700
Data Index: 4958780 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.6283. Min Act: -0.1700
Data Index: 8701721 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.5658. Min Act: -0.1700
Data Index: 3096757 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.5658. Min Act: -0.1700
Data Index: 8388427 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4095. Min Range: -6.4095
Max Act: 5.5970. Min Act: -0.1700
Data Index: 5928478 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19