Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2574 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3543. Min Range: -8.3543
Max Act: 8.3543. Min Act: -0.1700
Data Index: 5552424 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.6668. Min Act: -0.1700
Data Index: 3626889 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.6355. Min Act: -0.1700
Data Index: 2566780 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.6355. Min Act: -0.1700
Data Index: 4261295 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.5105. Min Act: -0.1700
Data Index: 1243800 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.4480. Min Act: -0.1700
Data Index: 8366835 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.4480. Min Act: -0.1700
Data Index: 3704134 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.4480. Min Act: -0.1700
Data Index: 6599254 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.3855. Min Act: -0.1700
Data Index: 3981884 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.2918. Min Act: -0.1700
Data Index: 2761585 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.2918. Min Act: -0.1700
Data Index: 6996091 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.2293. Min Act: -0.1700
Data Index: 6861803 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.1668. Min Act: -0.1700
Data Index: 548594 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.1668. Min Act: -0.1700
Data Index: 338793 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.1043. Min Act: -0.1700
Data Index: 6463157 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.1043. Min Act: -0.1700
Data Index: 2154845 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.1043. Min Act: -0.1700
Data Index: 701129 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.0730. Min Act: -0.1700
Data Index: 3878914 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.0730. Min Act: -0.1700
Data Index: 7180291 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3543. Min Range: -8.3543
Max Act: 7.0730. Min Act: -0.1700
Data Index: 1263231 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19