Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5617 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.8984. Min Act: -0.1700
Data Index: 2996628 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.8359. Min Act: -0.1700
Data Index: 2077634 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.6171. Min Act: -0.1700
Data Index: 799748 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.5546. Min Act: -0.1700
Data Index: 316631 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.5234. Min Act: -0.1700
Data Index: 7193277 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.5234. Min Act: -0.1700
Data Index: 660830 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.4921. Min Act: -0.1700
Data Index: 511217 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.4609. Min Act: -0.1700
Data Index: 4905316 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.4921. Min Act: -0.1700
Data Index: 4997459 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.4609. Min Act: -0.1700
Data Index: 1235593 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.4296. Min Act: -0.1700
Data Index: 6970581 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.4296. Min Act: -0.1700
Data Index: 148244 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.3671. Min Act: -0.1700
Data Index: 2998903 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.3671. Min Act: -0.1700
Data Index: 6379715 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.3671. Min Act: -0.1700
Data Index: 3526967 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.3984. Min Act: -0.1700
Data Index: 3309123 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.3359. Min Act: -0.1700
Data Index: 6013375 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.3046. Min Act: -0.1700
Data Index: 7311306 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.2734. Min Act: -0.1700
Data Index: 6013376 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8984. Min Range: -5.8984
Max Act: 5.2734. Min Act: -0.1700
Data Index: 6992378 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19