Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3005 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.3660. Min Act: -0.1700
Data Index: 3614581 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.2090. Min Act: -0.1700
Data Index: 2556723 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.1933. Min Act: -0.1700
Data Index: 5125666 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.1775. Min Act: -0.1700
Data Index: 8087216 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.1461. Min Act: -0.1700
Data Index: 2228298 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.1618. Min Act: -0.1700
Data Index: 8592664 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.1461. Min Act: -0.1700
Data Index: 5301791 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.1303. Min Act: -0.1700
Data Index: 5352051 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.1146. Min Act: -0.1700
Data Index: 8050284 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.1146. Min Act: -0.1700
Data Index: 6644867 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.1146. Min Act: -0.1700
Data Index: 5800840 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.0988. Min Act: -0.1700
Data Index: 7536950 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.0830. Min Act: -0.1700
Data Index: 6540978 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.0830. Min Act: -0.1700
Data Index: 3626526 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.0830. Min Act: -0.1700
Data Index: 2504034 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.0515. Min Act: -0.1700
Data Index: 700465 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.0515. Min Act: -0.1700
Data Index: 7231968 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.0357. Min Act: -0.1700
Data Index: 5239015 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.0357. Min Act: -0.1700
Data Index: 7328020 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3660. Min Range: -3.3660
Max Act: 3.0357. Min Act: -0.1700
Data Index: 6733848 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19