Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 756 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.9555. Min Act: -0.1700
Data Index: 371558 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.6743. Min Act: -0.1700
Data Index: 342607 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.6118. Min Act: -0.1700
Data Index: 6605711 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.5805. Min Act: -0.1700
Data Index: 1973062 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.5805. Min Act: -0.1700
Data Index: 166601 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.5493. Min Act: -0.1700
Data Index: 7747193 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.5180. Min Act: -0.1700
Data Index: 104899 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.5180. Min Act: -0.1700
Data Index: 4004310 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.4868. Min Act: -0.1700
Data Index: 1298615 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.4868. Min Act: -0.1700
Data Index: 242545 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.4868. Min Act: -0.1700
Data Index: 7595733 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.4555. Min Act: -0.1700
Data Index: 7075505 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.4555. Min Act: -0.1700
Data Index: 3491689 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.4243. Min Act: -0.1700
Data Index: 6817107 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.3930. Min Act: -0.1700
Data Index: 2505234 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.3930. Min Act: -0.1700
Data Index: 5641304 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.3930. Min Act: -0.1700
Data Index: 5554699 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.3930. Min Act: -0.1700
Data Index: 1726298 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.3930. Min Act: -0.1700
Data Index: 1605117 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9555. Min Range: -5.9555
Max Act: 5.3930. Min Act: -0.1700
Data Index: 1618422 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #19