Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4830 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1156. Min Range: -5.1156
Max Act: 5.1156. Min Act: -0.1700
Data Index: 762789 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1156. Min Range: -5.1156
Max Act: 5.0844. Min Act: -0.1700
Data Index: 722250 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1156. Min Range: -5.1156
Max Act: 5.0531. Min Act: -0.1700
Data Index: 6422684 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.9906. Min Act: -0.1700
Data Index: 6734096 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.9594. Min Act: -0.1700
Data Index: 7789154 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.9281. Min Act: -0.1700
Data Index: 8772839 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.8969. Min Act: -0.1700
Data Index: 7751231 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.8656. Min Act: -0.1700
Data Index: 5264450 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.8656. Min Act: -0.1700
Data Index: 4950650 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.8656. Min Act: -0.1700
Data Index: 1841831 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.8656. Min Act: -0.1700
Data Index: 3347003 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.8344. Min Act: -0.1700
Data Index: 1571094 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.8344. Min Act: -0.1700
Data Index: 4073719 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7719. Min Act: -0.1700
Data Index: 6915109 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7719. Min Act: -0.1700
Data Index: 4533208 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7406. Min Act: -0.1700
Data Index: 4971545 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7406. Min Act: -0.1700
Data Index: 2966414 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7094. Min Act: -0.1700
Data Index: 8513681 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7406. Min Act: -0.1700
Data Index: 7697806 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1156. Min Range: -5.1156
Max Act: 4.7094. Min Act: -0.1700
Data Index: 2826356 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19