Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3418 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.6570. Min Act: -0.1700
Data Index: 913115 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.6258. Min Act: -0.1700
Data Index: 6354900 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.5945. Min Act: -0.1700
Data Index: 3224405 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.5945. Min Act: -0.1700
Data Index: 5340020 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.5320. Min Act: -0.1700
Data Index: 67629 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.5633. Min Act: -0.1700
Data Index: 5134428 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.5320. Min Act: -0.1700
Data Index: 1765147 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.5320. Min Act: -0.1700
Data Index: 5183813 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.5320. Min Act: -0.1700
Data Index: 2994896 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.5320. Min Act: -0.1700
Data Index: 2721222 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.5008. Min Act: -0.1700
Data Index: 7281012 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.4695. Min Act: -0.1700
Data Index: 8114415 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.4695. Min Act: -0.1700
Data Index: 5984785 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.4695. Min Act: -0.1700
Data Index: 2225887 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.3758. Min Act: -0.1700
Data Index: 5030051 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.3758. Min Act: -0.1700
Data Index: 5243469 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.3758. Min Act: -0.1700
Data Index: 467848 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.3445. Min Act: -0.1700
Data Index: 6431558 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.3445. Min Act: -0.1700
Data Index: 3435276 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6570. Min Range: -5.6570
Max Act: 5.3445. Min Act: -0.1700
Data Index: 7492241 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19