Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4789 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.4726. Min Act: -0.1700
Data Index: 416274 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.4726. Min Act: -0.1700
Data Index: 749854 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.4569. Min Act: -0.1700
Data Index: 6076770 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.4413. Min Act: -0.1700
Data Index: 4346912 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.4256. Min Act: -0.1700
Data Index: 8487335 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.4413. Min Act: -0.1700
Data Index: 2941641 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.4256. Min Act: -0.1700
Data Index: 1720737 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3942. Min Act: -0.1700
Data Index: 7934840 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3942. Min Act: -0.1700
Data Index: 6726330 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3786. Min Act: -0.1700
Data Index: 8445145 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3786. Min Act: -0.1700
Data Index: 7339372 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3786. Min Act: -0.1700
Data Index: 7198691 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3786. Min Act: -0.1700
Data Index: 534173 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3472. Min Act: -0.1700
Data Index: 3795424 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3786. Min Act: -0.1700
Data Index: 7598750 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3472. Min Act: -0.1700
Data Index: 534171 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3158. Min Act: -0.1700
Data Index: 5207298 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3315. Min Act: -0.1700
Data Index: 1497288 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3472. Min Act: -0.1700
Data Index: 3408311 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4726. Min Range: -3.4726
Max Act: 3.3315. Min Act: -0.1700
Data Index: 7680822 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #19