Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1771 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.7662. Min Act: -0.1700
Data Index: 4517963 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.7662. Min Act: -0.1700
Data Index: 8090034 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.6412. Min Act: -0.1700
Data Index: 1093731 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.5787. Min Act: -0.1700
Data Index: 1267975 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.5787. Min Act: -0.1700
Data Index: 408877 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.5787. Min Act: -0.1700
Data Index: 5652757 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.5787. Min Act: -0.1700
Data Index: 2453740 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.5787. Min Act: -0.1700
Data Index: 6441724 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.5474. Min Act: -0.1700
Data Index: 6522807 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.5162. Min Act: -0.1700
Data Index: 4856473 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.4849. Min Act: -0.1700
Data Index: 5556768 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.4849. Min Act: -0.1700
Data Index: 7076079 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.4537. Min Act: -0.1700
Data Index: 645551 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.4537. Min Act: -0.1700
Data Index: 7844724 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.4849. Min Act: -0.1700
Data Index: 5278110 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.4224. Min Act: -0.1700
Data Index: 7288657 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.4224. Min Act: -0.1700
Data Index: 7336798 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.4224. Min Act: -0.1700
Data Index: 8675201 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.3912. Min Act: -0.1700
Data Index: 6448052 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7662. Min Range: -4.7662
Max Act: 4.4224. Min Act: -0.1700
Data Index: 8064806 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #19