Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3373 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2443. Min Range: -6.2443
Max Act: 6.2443. Min Act: -0.1700
Data Index: 1348660 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2443. Min Range: -6.2443
Max Act: 6.1818. Min Act: -0.1700
Data Index: 4786579 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2443. Min Range: -6.2443
Max Act: 6.0568. Min Act: -0.1700
Data Index: 6696313 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.9943. Min Act: -0.1700
Data Index: 5242866 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.9630. Min Act: -0.1700
Data Index: 8231855 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.9630. Min Act: -0.1700
Data Index: 4416479 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.9943. Min Act: -0.1700
Data Index: 4224621 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.9630. Min Act: -0.1700
Data Index: 6325362 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.9318. Min Act: -0.1700
Data Index: 7316933 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.9318. Min Act: -0.1700
Data Index: 2041263 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.9005. Min Act: -0.1700
Data Index: 7708017 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.8693. Min Act: -0.1700
Data Index: 8502872 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.8693. Min Act: -0.1700
Data Index: 3157279 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.8068. Min Act: -0.1700
Data Index: 1363027 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.8380. Min Act: -0.1700
Data Index: 7141362 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.8693. Min Act: -0.1700
Data Index: 108245 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.8068. Min Act: -0.1700
Data Index: 4982547 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.8068. Min Act: -0.1700
Data Index: 5973130 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.8068. Min Act: -0.1700
Data Index: 1086348 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2443. Min Range: -6.2443
Max Act: 5.7755. Min Act: -0.1700
Data Index: 7896329 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19