Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2537 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.6684. Min Act: -0.1700
Data Index: 4200404 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.6684. Min Act: -0.1700
Data Index: 5579135 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.5434. Min Act: -0.1700
Data Index: 4483229 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.5434. Min Act: -0.1700
Data Index: 7652174 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.5434. Min Act: -0.1700
Data Index: 4380095 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.5121. Min Act: -0.1700
Data Index: 2204826 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.5121. Min Act: -0.1700
Data Index: 3406708 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.4496. Min Act: -0.1700
Data Index: 7946402 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.4496. Min Act: -0.1700
Data Index: 7684684 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.4184. Min Act: -0.1700
Data Index: 4336704 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.3871. Min Act: -0.1700
Data Index: 6024438 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.3871. Min Act: -0.1700
Data Index: 7738583 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.3246. Min Act: -0.1700
Data Index: 8793891 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.3246. Min Act: -0.1700
Data Index: 2905484 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.2934. Min Act: -0.1700
Data Index: 815196 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.2934. Min Act: -0.1700
Data Index: 3326753 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.2621. Min Act: -0.1700
Data Index: 7171185 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.2621. Min Act: -0.1700
Data Index: 7680867 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.2621. Min Act: -0.1700
Data Index: 7629118 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6684. Min Range: -4.6684
Max Act: 4.2621. Min Act: -0.1700
Data Index: 6803268 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19