Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3423 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.4826. Min Act: -0.1700
Data Index: 6041606 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.4826. Min Act: -0.1700
Data Index: 5182947 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.3888. Min Act: -0.1700
Data Index: 5531350 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.3576. Min Act: -0.1700
Data Index: 7195990 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.3576. Min Act: -0.1700
Data Index: 6230656 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.3576. Min Act: -0.1700
Data Index: 4315097 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.3888. Min Act: -0.1700
Data Index: 4561953 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.3576. Min Act: -0.1700
Data Index: 4762146 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.3576. Min Act: -0.1700
Data Index: 2760445 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.3263. Min Act: -0.1700
Data Index: 284065 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.3263. Min Act: -0.1700
Data Index: 8247454 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.3263. Min Act: -0.1700
Data Index: 7552812 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.3263. Min Act: -0.1700
Data Index: 6883125 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.2951. Min Act: -0.1700
Data Index: 912 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.2951. Min Act: -0.1700
Data Index: 8231371 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.2951. Min Act: -0.1700
Data Index: 5951382 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.2638. Min Act: -0.1700
Data Index: 2760442 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.2638. Min Act: -0.1700
Data Index: 1508411 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.2638. Min Act: -0.1700
Data Index: 5412706 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4826. Min Range: -5.4826
Max Act: 5.2638. Min Act: -0.1700
Data Index: 1726256 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19