Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1682 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.6100. Min Act: -0.1700
Data Index: 3161755 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.5788. Min Act: -0.1700
Data Index: 6930236 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.5163. Min Act: -0.1700
Data Index: 8710675 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.4850. Min Act: -0.1700
Data Index: 218164 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.4850. Min Act: -0.1700
Data Index: 4278385 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.4538. Min Act: -0.1700
Data Index: 8639296 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.4538. Min Act: -0.1700
Data Index: 2106462 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.4225. Min Act: -0.1700
Data Index: 4763259 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.4225. Min Act: -0.1700
Data Index: 592251 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.3913. Min Act: -0.1700
Data Index: 3039736 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.3913. Min Act: -0.1700
Data Index: 6750360 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.4225. Min Act: -0.1700
Data Index: 7041958 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.3913. Min Act: -0.1700
Data Index: 7597669 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.3913. Min Act: -0.1700
Data Index: 3269431 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.3913. Min Act: -0.1696
Data Index: 5189335 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.3288. Min Act: -0.1700
Data Index: 4333593 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.3600. Min Act: -0.1700
Data Index: 1347262 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.3600. Min Act: -0.1700
Data Index: 6474236 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.3600. Min Act: -0.1700
Data Index: 4809576 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6100. Min Range: -5.6100
Max Act: 5.3600. Min Act: -0.1700
Data Index: 7775481 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19