Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5508 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.7375. Min Act: -0.1700
Data Index: 8819064 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.6750. Min Act: -0.1700
Data Index: 5995890 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.6125. Min Act: -0.1700
Data Index: 7833951 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.5500. Min Act: -0.1700
Data Index: 5376754 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.5500. Min Act: -0.1700
Data Index: 2198299 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.5500. Min Act: -0.1700
Data Index: 798512 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.5500. Min Act: -0.1700
Data Index: 6335904 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.4250. Min Act: -0.1700
Data Index: 6807832 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.4250. Min Act: -0.1700
Data Index: 802244 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.4250. Min Act: -0.1700
Data Index: 3229546 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.4250. Min Act: -0.1700
Data Index: 2683201 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.3625. Min Act: -0.1700
Data Index: 245521 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.3625. Min Act: -0.1700
Data Index: 710360 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.3625. Min Act: -0.1700
Data Index: 2045255 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.3000. Min Act: -0.1700
Data Index: 2711972 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.3000. Min Act: -0.1700
Data Index: 3583009 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.3000. Min Act: -0.1700
Data Index: 370985 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.3000. Min Act: -0.1700
Data Index: 5747353 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.3000. Min Act: -0.1700
Data Index: 1495900 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7375. Min Range: -8.7375
Max Act: 8.2375. Min Act: -0.1700
Data Index: 4452638 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19