Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2580 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.6323. Min Act: -0.1700
Data Index: 8720733 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.6323. Min Act: -0.1700
Data Index: 4688548 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.6323. Min Act: -0.1700
Data Index: 8754830 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.6011. Min Act: -0.1700
Data Index: 3903214 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.6323. Min Act: -0.1700
Data Index: 480791 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.6011. Min Act: -0.1700
Data Index: 7341139 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.5386. Min Act: -0.1700
Data Index: 6497671 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.5698. Min Act: -0.1700
Data Index: 1286701 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.5698. Min Act: -0.1700
Data Index: 8725969 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.5698. Min Act: -0.1700
Data Index: 5819215 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.5698. Min Act: -0.1700
Data Index: 6135578 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.5386. Min Act: -0.1700
Data Index: 5802689 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.5073. Min Act: -0.1700
Data Index: 2504619 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.5073. Min Act: -0.1700
Data Index: 6589275 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.3198. Min Act: -0.1700
Data Index: 913787 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.2573. Min Act: -0.1700
Data Index: 8066355 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.2261. Min Act: -0.1700
Data Index: 3969910 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1636. Min Act: -0.1700
Data Index: 2593356 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1323. Min Act: -0.1700
Data Index: 8338339 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6323. Min Range: -6.6323
Max Act: 6.1323. Min Act: -0.1700
Data Index: 7427704 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19