Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 121 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.6631. Min Act: -0.1700
Data Index: 1646112 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.2568. Min Act: -0.1700
Data Index: 8144679 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.1943. Min Act: -0.1700
Data Index: 4546790 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.1943. Min Act: -0.1700
Data Index: 1601943 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.1943. Min Act: -0.1700
Data Index: 2269248 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.1943. Min Act: -0.1700
Data Index: 1707103 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.0693. Min Act: -0.1700
Data Index: 1615853 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.0693. Min Act: -0.1700
Data Index: 5563981 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.0381. Min Act: -0.1700
Data Index: 7126737 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.0381. Min Act: -0.1700
Data Index: 8832376 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.0068. Min Act: -0.1700
Data Index: 912164 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6631. Min Range: -5.6631
Max Act: 4.9756. Min Act: -0.1700
Data Index: 2937287 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6631. Min Range: -5.6631
Max Act: 4.9756. Min Act: -0.1700
Data Index: 3299160 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6631. Min Range: -5.6631
Max Act: 4.9756. Min Act: -0.1700
Data Index: 5422902 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6631. Min Range: -5.6631
Max Act: 4.9756. Min Act: -0.1700
Data Index: 6229239 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6631. Min Range: -5.6631
Max Act: 5.0068. Min Act: -0.1700
Data Index: 6673175 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6631. Min Range: -5.6631
Max Act: 4.9756. Min Act: -0.1700
Data Index: 6944239 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6631. Min Range: -5.6631
Max Act: 4.9756. Min Act: -0.1700
Data Index: 3980703 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6631. Min Range: -5.6631
Max Act: 4.9443. Min Act: -0.1700
Data Index: 7640224 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6631. Min Range: -5.6631
Max Act: 4.9443. Min Act: -0.1700
Data Index: 1494955 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19