Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2899 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.9693. Min Act: -0.1700
Data Index: 576061 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.8755. Min Act: -0.1700
Data Index: 2573627 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.8443. Min Act: -0.1700
Data Index: 4780948 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.8443. Min Act: -0.1700
Data Index: 5961481 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7818. Min Act: -0.1700
Data Index: 5381664 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7505. Min Act: -0.1700
Data Index: 4600726 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.7193. Min Act: -0.1700
Data Index: 2443550 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6568. Min Act: -0.1700
Data Index: 5552870 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6568. Min Act: -0.1700
Data Index: 7424459 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6568. Min Act: -0.1700
Data Index: 7182588 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6568. Min Act: -0.1700
Data Index: 7734606 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6568. Min Act: -0.1700
Data Index: 3732573 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6255. Min Act: -0.1700
Data Index: 7192468 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6568. Min Act: -0.1700
Data Index: 4148692 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6255. Min Act: -0.1700
Data Index: 3146473 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.6255. Min Act: -0.1700
Data Index: 3393787 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.5943. Min Act: -0.1700
Data Index: 356490 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.5943. Min Act: -0.1700
Data Index: 7087441 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.5318. Min Act: -0.1700
Data Index: 7785462 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9693. Min Range: -5.9693
Max Act: 5.5943. Min Act: -0.1700
Data Index: 7185684 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #19