Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3603 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4025. Min Range: -7.4025
Max Act: 7.4025. Min Act: -0.1700
Data Index: 1398355 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4025. Min Range: -7.4025
Max Act: 7.2775. Min Act: -0.1700
Data Index: 6501258 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4025. Min Range: -7.4025
Max Act: 7.1213. Min Act: -0.1700
Data Index: 7667595 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4025. Min Range: -7.4025
Max Act: 7.1525. Min Act: -0.1700
Data Index: 5280668 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4025. Min Range: -7.4025
Max Act: 7.0900. Min Act: -0.1700
Data Index: 501447 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.9650. Min Act: -0.1700
Data Index: 6453083 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.9650. Min Act: -0.1700
Data Index: 4466721 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.9338. Min Act: -0.1700
Data Index: 4206587 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.9338. Min Act: -0.1700
Data Index: 8725085 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.9338. Min Act: -0.1700
Data Index: 3224780 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.8713. Min Act: -0.1700
Data Index: 8065541 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.9025. Min Act: -0.1700
Data Index: 3591387 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.8713. Min Act: -0.1700
Data Index: 1569887 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.8400. Min Act: -0.1700
Data Index: 3694660 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.8400. Min Act: -0.1700
Data Index: 5840682 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.8088. Min Act: -0.1700
Data Index: 4507845 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.7775. Min Act: -0.1700
Data Index: 3283315 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.7775. Min Act: -0.1700
Data Index: 7794621 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.7463. Min Act: -0.1700
Data Index: 794970 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4025. Min Range: -7.4025
Max Act: 6.7463. Min Act: -0.1700
Data Index: 1727956 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19