Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2917 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.8337. Min Act: -0.1700
Data Index: 8390734 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.7867. Min Act: -0.1700
Data Index: 371628 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.7398. Min Act: -0.1700
Data Index: 7196889 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.6773. Min Act: -0.1700
Data Index: 8151480 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.6929. Min Act: -0.1700
Data Index: 4623704 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.6616. Min Act: -0.1700
Data Index: 8033647 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.6147. Min Act: -0.1700
Data Index: 4155021 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.5521. Min Act: -0.1700
Data Index: 7544561 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.5364. Min Act: -0.1700
Data Index: 2592040 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.4738. Min Act: -0.1700
Data Index: 3058001 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.4738. Min Act: -0.1700
Data Index: 4303929 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.4581. Min Act: -0.1700
Data Index: 3393272 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.4267. Min Act: -0.1700
Data Index: 2844681 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.4267. Min Act: -0.1700
Data Index: 2990494 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.4111. Min Act: -0.1700
Data Index: 3943565 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.4111. Min Act: -0.1700
Data Index: 3630085 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.3954. Min Act: -0.1700
Data Index: 4706313 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.3954. Min Act: -0.1700
Data Index: 1954720 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.3954. Min Act: -0.1700
Data Index: 6715600 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8337. Min Range: -3.8337
Max Act: 3.3797. Min Act: -0.1700
Data Index: 5709605 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19