Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5599 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.9170. Min Act: -0.1700
Data Index: 4972111 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.8857. Min Act: -0.1700
Data Index: 7301345 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.8232. Min Act: -0.1700
Data Index: 2002563 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.7607. Min Act: -0.1700
Data Index: 8402066 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.7607. Min Act: -0.1700
Data Index: 4618599 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.7295. Min Act: -0.1700
Data Index: 1298248 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.7295. Min Act: -0.1700
Data Index: 1132113 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.6982. Min Act: -0.1700
Data Index: 3012813 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.6982. Min Act: -0.1700
Data Index: 5136230 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.6982. Min Act: -0.1700
Data Index: 4946348 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.6670. Min Act: -0.1700
Data Index: 758223 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.6670. Min Act: -0.1700
Data Index: 2551481 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.6670. Min Act: -0.1700
Data Index: 821331 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.6357. Min Act: -0.1700
Data Index: 801170 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.6045. Min Act: -0.1700
Data Index: 8497110 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.6045. Min Act: -0.1700
Data Index: 1359961 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.5732. Min Act: -0.1700
Data Index: 1861593 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.5420. Min Act: -0.1700
Data Index: 4463721 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.5732. Min Act: -0.1700
Data Index: 3669930 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9170. Min Range: -5.9170
Max Act: 5.5732. Min Act: -0.1700
Data Index: 1714873 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19