Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4637 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.8522. Min Act: -0.1700
Data Index: 4589693 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.7897. Min Act: -0.1700
Data Index: 7359271 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.7585. Min Act: -0.1700
Data Index: 3892210 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.7585. Min Act: -0.1700
Data Index: 4513476 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.6960. Min Act: -0.1700
Data Index: 4200998 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.6960. Min Act: -0.1700
Data Index: 231341 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.6647. Min Act: -0.1700
Data Index: 4606160 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.6022. Min Act: -0.1700
Data Index: 8535635 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.6022. Min Act: -0.1700
Data Index: 7543132 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5710. Min Act: -0.1700
Data Index: 6768682 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5710. Min Act: -0.1700
Data Index: 6828142 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5397. Min Act: -0.1700
Data Index: 5042990 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5397. Min Act: -0.1700
Data Index: 7820386 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5397. Min Act: -0.1700
Data Index: 3929810 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5397. Min Act: -0.1700
Data Index: 6791993 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5085. Min Act: -0.1700
Data Index: 2336904 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5397. Min Act: -0.1700
Data Index: 6011303 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5085. Min Act: -0.1700
Data Index: 1681778 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.5085. Min Act: -0.1700
Data Index: 2393943 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8522. Min Range: -5.8522
Max Act: 5.4772. Min Act: -0.1700
Data Index: 390963 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #19