Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2984 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3334. Min Range: -8.3334
Max Act: 8.3334. Min Act: -0.1700
Data Index: 1693719 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3334. Min Range: -8.3334
Max Act: 8.2084. Min Act: -0.1700
Data Index: 2480804 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3334. Min Range: -8.3334
Max Act: 8.1459. Min Act: -0.1700
Data Index: 372694 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3334. Min Range: -8.3334
Max Act: 8.1459. Min Act: -0.1700
Data Index: 8479312 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.9896. Min Act: -0.1700
Data Index: 7002464 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.8646. Min Act: -0.1700
Data Index: 6989783 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.8334. Min Act: -0.1700
Data Index: 3839374 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.8021. Min Act: -0.1700
Data Index: 5850885 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.8021. Min Act: -0.1700
Data Index: 6910334 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.6459. Min Act: -0.1700
Data Index: 2025863 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.5834. Min Act: -0.1700
Data Index: 2296377 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.5209. Min Act: -0.1700
Data Index: 4089196 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.4896. Min Act: -0.1700
Data Index: 3302418 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.4896. Min Act: -0.1700
Data Index: 6541591 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.5209. Min Act: -0.1700
Data Index: 7589449 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.4896. Min Act: -0.1700
Data Index: 3646373 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.4584. Min Act: -0.1700
Data Index: 4192887 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.4271. Min Act: -0.1700
Data Index: 4814761 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.3959. Min Act: -0.1700
Data Index: 3944951 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3334. Min Range: -8.3334
Max Act: 7.3646. Min Act: -0.1700
Data Index: 7772773 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19