Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1586 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.8584. Min Act: -0.1700
Data Index: 8132435 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.8584. Min Act: -0.1700
Data Index: 4243872 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.7646. Min Act: -0.1700
Data Index: 160801 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.6084. Min Act: -0.1700
Data Index: 2986349 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.5771. Min Act: -0.1700
Data Index: 5449642 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.5459. Min Act: -0.1700
Data Index: 2293183 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.5146. Min Act: -0.1700
Data Index: 8099280 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.5146. Min Act: -0.1700
Data Index: 4243470 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.5146. Min Act: -0.1700
Data Index: 5120572 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.4521. Min Act: -0.1700
Data Index: 6677057 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.4521. Min Act: -0.1700
Data Index: 4194577 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.4521. Min Act: -0.1700
Data Index: 3474295 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.4208. Min Act: -0.1700
Data Index: 2468103 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.3896. Min Act: -0.1700
Data Index: 3469585 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.3896. Min Act: -0.1700
Data Index: 4780066 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.3896. Min Act: -0.1700
Data Index: 8174794 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.3896. Min Act: -0.1700
Data Index: 4464384 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.3896. Min Act: -0.1700
Data Index: 3705690 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.3896. Min Act: -0.1700
Data Index: 8062964 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8584. Min Range: -4.8584
Max Act: 4.3583. Min Act: -0.1700
Data Index: 4733550 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #19