Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2590 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.7656. Min Act: -0.1700
Data Index: 1257971 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.6406. Min Act: -0.1700
Data Index: 3126623 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.6406. Min Act: -0.1700
Data Index: 1679110 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.6406. Min Act: -0.1700
Data Index: 3893079 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.5156. Min Act: -0.1700
Data Index: 6481903 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.3906. Min Act: -0.1700
Data Index: 3463043 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.3906. Min Act: -0.1700
Data Index: 5387165 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.3594. Min Act: -0.1700
Data Index: 3073351 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.3594. Min Act: -0.1700
Data Index: 7220267 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.2969. Min Act: -0.1700
Data Index: 8684402 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.3281. Min Act: -0.1700
Data Index: 7932008 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.3281. Min Act: -0.1700
Data Index: 2864616 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.2969. Min Act: -0.1700
Data Index: 2141827 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.2969. Min Act: -0.1700
Data Index: 8253999 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.2656. Min Act: -0.1700
Data Index: 419104 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.2344. Min Act: -0.1700
Data Index: 880341 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.2344. Min Act: -0.1700
Data Index: 7774438 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.2344. Min Act: -0.1700
Data Index: 7615451 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.2031. Min Act: -0.1700
Data Index: 6809722 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7656. Min Range: -5.7656
Max Act: 5.2031. Min Act: -0.1700
Data Index: 3450270 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #19