Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2511 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.6741. Min Act: -0.1700
Data Index: 1669014 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.6429. Min Act: -0.1700
Data Index: 4898843 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.5959. Min Act: -0.1700
Data Index: 4071342 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.5803. Min Act: -0.1700
Data Index: 7350598 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.5333. Min Act: -0.1700
Data Index: 301705 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.5020. Min Act: -0.1700
Data Index: 7966708 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.5020. Min Act: -0.1700
Data Index: 4853812 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.4706. Min Act: -0.1700
Data Index: 1830129 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.5020. Min Act: -0.1700
Data Index: 4476900 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.4550. Min Act: -0.1700
Data Index: 4385631 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.4550. Min Act: -0.1700
Data Index: 6771634 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.4236. Min Act: -0.1700
Data Index: 4947018 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.4236. Min Act: -0.1700
Data Index: 432805 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.4236. Min Act: -0.1700
Data Index: 7069278 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.3923. Min Act: -0.1700
Data Index: 6685408 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.3923. Min Act: -0.1700
Data Index: 4629090 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.3923. Min Act: -0.1700
Data Index: 2174151 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.3923. Min Act: -0.1700
Data Index: 3521342 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.3766. Min Act: -0.1700
Data Index: 5463685 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6741. Min Range: -3.6741
Max Act: 3.3766. Min Act: -0.1700
Data Index: 4870780 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #19