Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2725 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.7360. Min Act: -0.1700
Data Index: 6491112 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.7048. Min Act: -0.1700
Data Index: 709481 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.5485. Min Act: -0.1700
Data Index: 3362988 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.5798. Min Act: -0.1700
Data Index: 8342970 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.5485. Min Act: -0.1700
Data Index: 53699 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.5485. Min Act: -0.1700
Data Index: 6326300 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.5485. Min Act: -0.1700
Data Index: 307275 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.5173. Min Act: -0.1700
Data Index: 5424677 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.5173. Min Act: -0.1700
Data Index: 607905 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.5173. Min Act: -0.1700
Data Index: 6262244 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.4860. Min Act: -0.1700
Data Index: 1589581 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.4860. Min Act: -0.1700
Data Index: 8763888 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.4548. Min Act: -0.1700
Data Index: 1782816 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.4860. Min Act: -0.1700
Data Index: 7154054 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.4548. Min Act: -0.1700
Data Index: 1478095 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.4548. Min Act: -0.1700
Data Index: 7063209 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.4548. Min Act: -0.1700
Data Index: 3571987 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.4235. Min Act: -0.1700
Data Index: 6296492 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.4548. Min Act: -0.1700
Data Index: 6596487 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7360. Min Range: -5.7360
Max Act: 5.4235. Min Act: -0.1700
Data Index: 2855278 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #19