Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4411 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 591 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 650 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 625 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 623 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 590 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 63 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 25 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 433 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 152 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 416 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 458 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 369 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 348 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 552 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 259 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 493 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 55 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 44 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 329 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1686. Min Range: -2.1686
Max Act: 2.1686. Min Act: -0.1700
Data Index: 484 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19