Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.9264. Min Act: -0.1700
Data Index: 8710595 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.7702. Min Act: -0.1700
Data Index: 4090237 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.7702. Min Act: -0.1700
Data Index: 8362678 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.7702. Min Act: -0.1700
Data Index: 4802524 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.7702. Min Act: -0.1700
Data Index: 4405602 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.7389. Min Act: -0.1700
Data Index: 6583821 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.7077. Min Act: -0.1700
Data Index: 6488385 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.6452. Min Act: -0.1700
Data Index: 1968129 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.6139. Min Act: -0.1700
Data Index: 6413825 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.6139. Min Act: -0.1700
Data Index: 2839088 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.5514. Min Act: -0.1700
Data Index: 7824438 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.5514. Min Act: -0.1700
Data Index: 3537362 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.5514. Min Act: -0.1700
Data Index: 5319587 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.4889. Min Act: -0.1700
Data Index: 3872485 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.4889. Min Act: -0.1700
Data Index: 8280190 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.4264. Min Act: -0.1700
Data Index: 4379937 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.4577. Min Act: -0.1700
Data Index: 4063326 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.4889. Min Act: -0.1700
Data Index: 3651644 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.4577. Min Act: -0.1700
Data Index: 3258207 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9264. Min Range: -4.9264
Max Act: 4.4264. Min Act: -0.1700
Data Index: 5670880 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19