Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5355 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0700. Min Range: -7.0700
Max Act: 7.0700. Min Act: -0.1700
Data Index: 4082305 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.9763. Min Act: -0.1700
Data Index: 7755460 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.8825. Min Act: -0.1700
Data Index: 586054 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.9138. Min Act: -0.1700
Data Index: 3154740 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.8825. Min Act: -0.1700
Data Index: 2297805 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.8513. Min Act: -0.1700
Data Index: 4279268 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.8200. Min Act: -0.1700
Data Index: 6346675 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.8200. Min Act: -0.1700
Data Index: 6676405 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.8200. Min Act: -0.1700
Data Index: 5496908 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.7575. Min Act: -0.1700
Data Index: 796872 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.7575. Min Act: -0.1700
Data Index: 7853020 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.7263. Min Act: -0.1700
Data Index: 852610 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.7263. Min Act: -0.1700
Data Index: 927117 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.6950. Min Act: -0.1700
Data Index: 2253745 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.7263. Min Act: -0.1700
Data Index: 6851976 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.7263. Min Act: -0.1700
Data Index: 1878011 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.7263. Min Act: -0.1700
Data Index: 979122 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.7263. Min Act: -0.1700
Data Index: 7886110 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.6950. Min Act: -0.1700
Data Index: 2052794 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0700. Min Range: -7.0700
Max Act: 6.6950. Min Act: -0.1700
Data Index: 3763172 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19