Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1772 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3186. Min Range: -6.3186
Max Act: 6.3186. Min Act: -0.1700
Data Index: 4610284 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3186. Min Range: -6.3186
Max Act: 6.2873. Min Act: -0.1700
Data Index: 1380378 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3186. Min Range: -6.3186
Max Act: 6.2873. Min Act: -0.1700
Data Index: 8686243 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3186. Min Range: -6.3186
Max Act: 6.1623. Min Act: -0.1700
Data Index: 7826774 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3186. Min Range: -6.3186
Max Act: 6.1311. Min Act: -0.1700
Data Index: 2876270 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3186. Min Range: -6.3186
Max Act: 6.0373. Min Act: -0.1700
Data Index: 127582 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3186. Min Range: -6.3186
Max Act: 6.0373. Min Act: -0.1700
Data Index: 8686242 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3186. Min Range: -6.3186
Max Act: 6.0373. Min Act: -0.1700
Data Index: 6109376 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3186. Min Range: -6.3186
Max Act: 6.0061. Min Act: -0.1700
Data Index: 721951 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3186. Min Range: -6.3186
Max Act: 5.9436. Min Act: -0.1700
Data Index: 721956 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3186. Min Range: -6.3186
Max Act: 5.9123. Min Act: -0.1700
Data Index: 8686244 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3186. Min Range: -6.3186
Max Act: 5.9123. Min Act: -0.1700
Data Index: 4211795 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3186. Min Range: -6.3186
Max Act: 5.8811. Min Act: -0.1700
Data Index: 2415617 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3186. Min Range: -6.3186
Max Act: 5.8498. Min Act: -0.1700
Data Index: 5276008 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3186. Min Range: -6.3186
Max Act: 5.8186. Min Act: -0.1700
Data Index: 4307144 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3186. Min Range: -6.3186
Max Act: 5.8186. Min Act: -0.1700
Data Index: 6246634 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3186. Min Range: -6.3186
Max Act: 5.7873. Min Act: -0.1700
Data Index: 7433479 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3186. Min Range: -6.3186
Max Act: 5.8186. Min Act: -0.1700
Data Index: 450701 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3186. Min Range: -6.3186
Max Act: 5.8186. Min Act: -0.1700
Data Index: 6137733 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3186. Min Range: -6.3186
Max Act: 5.7561. Min Act: -0.1700
Data Index: 8245298 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #19