Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1798. Min Range: -7.1798
Max Act: 7.1798. Min Act: -0.1700
Data Index: 1737607 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1798. Min Range: -7.1798
Max Act: 7.0860. Min Act: -0.1700
Data Index: 2272608 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.9298. Min Act: -0.1700
Data Index: 6563053 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.8985. Min Act: -0.1700
Data Index: 1702141 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.7735. Min Act: -0.1700
Data Index: 1424326 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.7423. Min Act: -0.1700
Data Index: 6619104 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.7110. Min Act: -0.1700
Data Index: 3930055 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.6485. Min Act: -0.1700
Data Index: 588440 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.6485. Min Act: -0.1700
Data Index: 4152565 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.6485. Min Act: -0.1700
Data Index: 7326392 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.6485. Min Act: -0.1700
Data Index: 8042077 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.6173. Min Act: -0.1700
Data Index: 7200616 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.5860. Min Act: -0.1700
Data Index: 5106499 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.5860. Min Act: -0.1700
Data Index: 8750304 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.6173. Min Act: -0.1700
Data Index: 1553427 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.4923. Min Act: -0.1700
Data Index: 6066750 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.5235. Min Act: -0.1700
Data Index: 177048 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.4923. Min Act: -0.1700
Data Index: 8518080 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.4923. Min Act: -0.1700
Data Index: 2866414 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1798. Min Range: -7.1798
Max Act: 6.4923. Min Act: -0.1700
Data Index: 8287322 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #19