Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1122 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.8060. Min Act: -0.1700
Data Index: 1555334 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.7747. Min Act: -0.1700
Data Index: 1904276 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.7747. Min Act: -0.1700
Data Index: 4420621 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.7747. Min Act: -0.1700
Data Index: 2802503 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.7435. Min Act: -0.1700
Data Index: 4779402 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.7122. Min Act: -0.1700
Data Index: 4718529 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.6810. Min Act: -0.1700
Data Index: 2456897 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.7122. Min Act: -0.1700
Data Index: 1703193 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.7122. Min Act: -0.1700
Data Index: 7676381 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.6810. Min Act: -0.1700
Data Index: 7667367 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.6810. Min Act: -0.1700
Data Index: 4888461 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.6810. Min Act: -0.1700
Data Index: 5310708 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.6497. Min Act: -0.1700
Data Index: 211125 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.6185. Min Act: -0.1700
Data Index: 2719695 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.6497. Min Act: -0.1700
Data Index: 4738457 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.6497. Min Act: -0.1700
Data Index: 6890401 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.6497. Min Act: -0.1700
Data Index: 3134842 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.6497. Min Act: -0.1700
Data Index: 5606018 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.6185. Min Act: -0.1700
Data Index: 174569 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8060. Min Range: -4.8060
Max Act: 4.6185. Min Act: -0.1700
Data Index: 2711310 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #19