Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1791 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.8134. Min Act: -0.1700
Data Index: 8387499 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.6884. Min Act: -0.1700
Data Index: 1477146 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.6259. Min Act: -0.1700
Data Index: 1696999 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.5009. Min Act: -0.1700
Data Index: 1479352 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.5009. Min Act: -0.1700
Data Index: 3015976 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.5009. Min Act: -0.1700
Data Index: 8447956 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.5009. Min Act: -0.1700
Data Index: 7562979 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.5009. Min Act: -0.1700
Data Index: 6764827 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.3759. Min Act: -0.1700
Data Index: 4812180 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.4384. Min Act: -0.1700
Data Index: 5397867 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.4384. Min Act: -0.1700
Data Index: 1951039 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.4384. Min Act: -0.1700
Data Index: 8215274 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.3759. Min Act: -0.1700
Data Index: 2975324 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.3759. Min Act: -0.1700
Data Index: 2775747 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.3759. Min Act: -0.1700
Data Index: 246265 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.3759. Min Act: -0.1700
Data Index: 1627358 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.3759. Min Act: -0.1700
Data Index: 5507090 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.3134. Min Act: -0.1700
Data Index: 3149115 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.3134. Min Act: -0.1700
Data Index: 1273635 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8134. Min Range: -9.8134
Max Act: 9.3134. Min Act: -0.1700
Data Index: 3135667 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #19