Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1128 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.7454. Min Act: -0.1700
Data Index: 4322348 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.7141. Min Act: -0.1700
Data Index: 512006 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6829. Min Act: -0.1700
Data Index: 422815 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6829. Min Act: -0.1700
Data Index: 2487523 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6829. Min Act: -0.1700
Data Index: 7083592 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.7141. Min Act: -0.1700
Data Index: 6829913 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6829. Min Act: -0.1700
Data Index: 5571411 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6516. Min Act: -0.1700
Data Index: 5908641 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6516. Min Act: -0.1700
Data Index: 6247864 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6516. Min Act: -0.1700
Data Index: 1878272 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6516. Min Act: -0.1700
Data Index: 1878269 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6516. Min Act: -0.1700
Data Index: 7518499 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6516. Min Act: -0.1700
Data Index: 7757212 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6516. Min Act: -0.1700
Data Index: 2233251 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6516. Min Act: -0.1700
Data Index: 3540411 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6516. Min Act: -0.1700
Data Index: 8402843 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6516. Min Act: -0.1700
Data Index: 685951 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6516. Min Act: -0.1700
Data Index: 8759519 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6829. Min Act: -0.1700
Data Index: 2792355 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7454. Min Range: -3.7454
Max Act: 3.6516. Min Act: -0.1700
Data Index: 8759520 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19