Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.9682. Min Act: -0.1700
Data Index: 5602883 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.8432. Min Act: -0.1700
Data Index: 1885656 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.4682. Min Act: -0.1700
Data Index: 6430289 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.4057. Min Act: -0.1700
Data Index: 3084206 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.3432. Min Act: -0.1700
Data Index: 7191864 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.2807. Min Act: -0.1700
Data Index: 8316824 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.2807. Min Act: -0.1700
Data Index: 5803418 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.1557. Min Act: -0.1700
Data Index: 6146403 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.0932. Min Act: -0.1700
Data Index: 4623328 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.1557. Min Act: -0.1700
Data Index: 4619071 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.1557. Min Act: -0.1700
Data Index: 2445378 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.1557. Min Act: -0.1700
Data Index: 5050983 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.1557. Min Act: -0.1700
Data Index: 958162 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.0932. Min Act: -0.1700
Data Index: 1667950 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.0932. Min Act: -0.1700
Data Index: 7891025 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.0932. Min Act: -0.1700
Data Index: 4468865 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.0307. Min Act: -0.1700
Data Index: 8750370 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9682. Min Range: -8.9682
Max Act: 8.0307. Min Act: -0.1700
Data Index: 7072090 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9682. Min Range: -8.9682
Max Act: 7.9682. Min Act: -0.1700
Data Index: 6804106 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9682. Min Range: -8.9682
Max Act: 7.9682. Min Act: -0.1700
Data Index: 4444274 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19