Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2476 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.3410. Min Act: -0.1700
Data Index: 5488415 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.3253. Min Act: -0.1700
Data Index: 5715676 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.3253. Min Act: -0.1700
Data Index: 5970416 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2625. Min Act: -0.1700
Data Index: 6163325 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2625. Min Act: -0.1700
Data Index: 2608905 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2625. Min Act: -0.1700
Data Index: 4050598 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2625. Min Act: -0.1700
Data Index: 1826204 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2625. Min Act: -0.1700
Data Index: 5055448 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2468. Min Act: -0.1700
Data Index: 2693868 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2468. Min Act: -0.1700
Data Index: 1265007 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2468. Min Act: -0.1700
Data Index: 42848 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2153. Min Act: -0.1700
Data Index: 1376199 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2311. Min Act: -0.1700
Data Index: 4516688 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2153. Min Act: -0.1700
Data Index: 6180754 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2468. Min Act: -0.1700
Data Index: 7911129 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1996. Min Act: -0.1700
Data Index: 7438819 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1839. Min Act: -0.1700
Data Index: 148221 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2153. Min Act: -0.1700
Data Index: 5187547 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.2153. Min Act: -0.1700
Data Index: 2242460 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3410. Min Range: -3.3410
Max Act: 3.1996. Min Act: -0.1700
Data Index: 2047734 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19