Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2970 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.7605. Min Act: -0.1700
Data Index: 509401 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.6043. Min Act: -0.1700
Data Index: 1211711 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.3855. Min Act: -0.1700
Data Index: 4928148 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.3230. Min Act: -0.1700
Data Index: 2014376 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.2918. Min Act: -0.1700
Data Index: 5708268 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.2605. Min Act: -0.1700
Data Index: 4692630 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.2918. Min Act: -0.1700
Data Index: 2316570 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.2605. Min Act: -0.1700
Data Index: 3471700 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.2918. Min Act: -0.1700
Data Index: 3501907 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.2605. Min Act: -0.1700
Data Index: 3402912 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.2918. Min Act: -0.1700
Data Index: 8759689 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.2605. Min Act: -0.1700
Data Index: 2206374 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.2293. Min Act: -0.1700
Data Index: 7373629 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.2605. Min Act: -0.1700
Data Index: 3914252 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.2293. Min Act: -0.1700
Data Index: 363106 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.1980. Min Act: -0.1700
Data Index: 2891434 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.1980. Min Act: -0.1700
Data Index: 7074363 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.1668. Min Act: -0.1700
Data Index: 6754055 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.1668. Min Act: -0.1700
Data Index: 97083 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7605. Min Range: -6.7605
Max Act: 6.1355. Min Act: -0.1700
Data Index: 2193971 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19