Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3897 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4320. Min Range: -8.4320
Max Act: 8.4320. Min Act: -0.1700
Data Index: 5007826 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4320. Min Range: -8.4320
Max Act: 8.2445. Min Act: -0.1700
Data Index: 6209903 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4320. Min Range: -8.4320
Max Act: 8.2445. Min Act: -0.1700
Data Index: 2388022 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4320. Min Range: -8.4320
Max Act: 8.1195. Min Act: -0.1700
Data Index: 7476296 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4320. Min Range: -8.4320
Max Act: 8.1195. Min Act: -0.1700
Data Index: 985279 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4320. Min Range: -8.4320
Max Act: 8.0570. Min Act: -0.1700
Data Index: 1382712 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.9633. Min Act: -0.1700
Data Index: 1047490 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4320. Min Range: -8.4320
Max Act: 8.0570. Min Act: -0.1700
Data Index: 1516829 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.8383. Min Act: -0.1700
Data Index: 7159347 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.7758. Min Act: -0.1700
Data Index: 3594130 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.7133. Min Act: -0.1700
Data Index: 5912765 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.7445. Min Act: -0.1700
Data Index: 5239654 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.6820. Min Act: -0.1700
Data Index: 1985254 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.6508. Min Act: -0.1700
Data Index: 2161951 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.6508. Min Act: -0.1700
Data Index: 5170639 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.6195. Min Act: -0.1700
Data Index: 5671951 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.6195. Min Act: -0.1700
Data Index: 2216000 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.6195. Min Act: -0.1700
Data Index: 7745676 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.5570. Min Act: -0.1700
Data Index: 7661933 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4320. Min Range: -8.4320
Max Act: 7.5570. Min Act: -0.1700
Data Index: 7833687 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #19