Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3583 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0741. Min Range: -5.0741
Max Act: 5.0741. Min Act: -0.1700
Data Index: 6856339 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0741. Min Range: -5.0741
Max Act: 5.0741. Min Act: -0.1700
Data Index: 1440239 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0741. Min Range: -5.0741
Max Act: 5.0741. Min Act: -0.1700
Data Index: 3185919 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0741. Min Range: -5.0741
Max Act: 5.0429. Min Act: -0.1700
Data Index: 7431933 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.8866. Min Act: -0.1700
Data Index: 3188569 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.8866. Min Act: -0.1700
Data Index: 2489136 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.9179. Min Act: -0.1700
Data Index: 8262996 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.8554. Min Act: -0.1700
Data Index: 4144037 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.8554. Min Act: -0.1700
Data Index: 2567320 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.8241. Min Act: -0.1700
Data Index: 6297545 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.8241. Min Act: -0.1700
Data Index: 6531136 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.7929. Min Act: -0.1700
Data Index: 4197827 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.7929. Min Act: -0.1700
Data Index: 3859578 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.7929. Min Act: -0.1700
Data Index: 7907854 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.7616. Min Act: -0.1700
Data Index: 2978399 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.7616. Min Act: -0.1700
Data Index: 5682610 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.7616. Min Act: -0.1700
Data Index: 5983683 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.7616. Min Act: -0.1700
Data Index: 4332082 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.7616. Min Act: -0.1700
Data Index: 5680831 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0741. Min Range: -5.0741
Max Act: 4.7616. Min Act: -0.1700
Data Index: 3960207 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19