Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3105 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0073. Min Range: -8.0073
Max Act: 8.0073. Min Act: -0.1700
Data Index: 7684173 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.7261. Min Act: -0.1700
Data Index: 7734968 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.6636. Min Act: -0.1700
Data Index: 4442095 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.6948. Min Act: -0.1700
Data Index: 796201 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.5698. Min Act: -0.1700
Data Index: 6359827 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.5073. Min Act: -0.1700
Data Index: 3742362 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.4448. Min Act: -0.1700
Data Index: 3308903 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.4448. Min Act: -0.1700
Data Index: 3738916 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.3823. Min Act: -0.1700
Data Index: 2053727 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.3511. Min Act: -0.1700
Data Index: 660567 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.3511. Min Act: -0.1700
Data Index: 8379742 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.3511. Min Act: -0.1700
Data Index: 182958 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.3511. Min Act: -0.1700
Data Index: 4706426 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.2886. Min Act: -0.1700
Data Index: 7079354 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.3198. Min Act: -0.1700
Data Index: 2478857 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.3198. Min Act: -0.1700
Data Index: 4013385 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.3198. Min Act: -0.1700
Data Index: 7295210 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.2886. Min Act: -0.1700
Data Index: 395349 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.2886. Min Act: -0.1700
Data Index: 6003963 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0073. Min Range: -8.0073
Max Act: 7.2886. Min Act: -0.1700
Data Index: 3722333 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #19