Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3253 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.7450. Min Act: -0.1700
Data Index: 3807582 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.8075. Min Act: -0.1700
Data Index: 5710239 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.6825. Min Act: -0.1700
Data Index: 5527537 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.6200. Min Act: -0.1700
Data Index: 7169532 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.5262. Min Act: -0.1700
Data Index: 8682453 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.5262. Min Act: -0.1700
Data Index: 2854409 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.4325. Min Act: -0.1700
Data Index: 5372402 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.4637. Min Act: -0.1700
Data Index: 2316108 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.4012. Min Act: -0.1700
Data Index: 5645901 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.4325. Min Act: -0.1700
Data Index: 4414860 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.4325. Min Act: -0.1700
Data Index: 373597 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.4012. Min Act: -0.1700
Data Index: 7312835 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.4012. Min Act: -0.1700
Data Index: 8357242 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.4012. Min Act: -0.1700
Data Index: 6334439 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.3700. Min Act: -0.1700
Data Index: 7294946 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.3700. Min Act: -0.1700
Data Index: 7011410 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.3700. Min Act: -0.1700
Data Index: 5558546 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.3700. Min Act: -0.1700
Data Index: 788831 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.3700. Min Act: -0.1700
Data Index: 5708414 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8075. Min Range: -7.8075
Max Act: 7.3700. Min Act: -0.1700
Data Index: 1548533 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19