Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4818 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6273. Min Range: -9.6273
Max Act: 9.6273. Min Act: -0.1700
Data Index: 3051227 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6273. Min Range: -9.6273
Max Act: 9.5023. Min Act: -0.1700
Data Index: 4149732 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6273. Min Range: -9.6273
Max Act: 9.2523. Min Act: -0.1700
Data Index: 3976030 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6273. Min Range: -9.6273
Max Act: 9.2523. Min Act: -0.1700
Data Index: 6254749 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6273. Min Range: -9.6273
Max Act: 9.1273. Min Act: -0.1700
Data Index: 126576 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.8773. Min Act: -0.1700
Data Index: 4269115 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.5648. Min Act: -0.1700
Data Index: 8312351 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.5023. Min Act: -0.1700
Data Index: 3884159 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.5023. Min Act: -0.1700
Data Index: 5976659 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.5023. Min Act: -0.1700
Data Index: 1967924 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.5023. Min Act: -0.1700
Data Index: 7365335 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.4398. Min Act: -0.1700
Data Index: 8757809 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.4398. Min Act: -0.1700
Data Index: 7266635 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.3773. Min Act: -0.1700
Data Index: 3484524 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.3773. Min Act: -0.1700
Data Index: 2318499 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.3773. Min Act: -0.1700
Data Index: 1953064 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.3773. Min Act: -0.1700
Data Index: 6837574 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.3148. Min Act: -0.1700
Data Index: 6625924 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.3773. Min Act: -0.1700
Data Index: 8657235 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6273. Min Range: -9.6273
Max Act: 8.3148. Min Act: -0.1700
Data Index: 8065097 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19