Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6185 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1646. Min Range: -6.1646
Max Act: 6.1646. Min Act: -0.1700
Data Index: 556642 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1646. Min Range: -6.1646
Max Act: 6.1334. Min Act: -0.1700
Data Index: 2641882 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1646. Min Range: -6.1646
Max Act: 6.1021. Min Act: -0.1700
Data Index: 3921085 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1646. Min Range: -6.1646
Max Act: 6.0396. Min Act: -0.1700
Data Index: 2315351 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1646. Min Range: -6.1646
Max Act: 6.0084. Min Act: -0.1700
Data Index: 4953955 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1646. Min Range: -6.1646
Max Act: 6.0396. Min Act: -0.1700
Data Index: 7789751 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1646. Min Range: -6.1646
Max Act: 6.0084. Min Act: -0.1700
Data Index: 7705001 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1646. Min Range: -6.1646
Max Act: 5.9771. Min Act: -0.1700
Data Index: 3905619 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1646. Min Range: -6.1646
Max Act: 6.0084. Min Act: -0.1700
Data Index: 6596327 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1646. Min Range: -6.1646
Max Act: 5.9459. Min Act: -0.1700
Data Index: 2925025 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1646. Min Range: -6.1646
Max Act: 5.9459. Min Act: -0.1700
Data Index: 1677853 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1646. Min Range: -6.1646
Max Act: 5.9459. Min Act: -0.1700
Data Index: 7720734 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1646. Min Range: -6.1646
Max Act: 5.9146. Min Act: -0.1700
Data Index: 658754 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1646. Min Range: -6.1646
Max Act: 5.9146. Min Act: -0.1700
Data Index: 148172 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1646. Min Range: -6.1646
Max Act: 5.8834. Min Act: -0.1700
Data Index: 6012890 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1646. Min Range: -6.1646
Max Act: 5.8834. Min Act: -0.1700
Data Index: 5598292 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1646. Min Range: -6.1646
Max Act: 5.8521. Min Act: -0.1700
Data Index: 6971531 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1646. Min Range: -6.1646
Max Act: 5.8521. Min Act: -0.1700
Data Index: 4352530 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1646. Min Range: -6.1646
Max Act: 5.8521. Min Act: -0.1700
Data Index: 2496017 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1646. Min Range: -6.1646
Max Act: 5.8521. Min Act: -0.1700
Data Index: 1146388 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19