Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5703 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0866. Min Range: -5.0866
Max Act: 5.0866. Min Act: -0.1700
Data Index: 8547105 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0866. Min Range: -5.0866
Max Act: 5.0554. Min Act: -0.1700
Data Index: 3504472 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.9304. Min Act: -0.1700
Data Index: 6964000 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.9304. Min Act: -0.1700
Data Index: 613150 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.9304. Min Act: -0.1700
Data Index: 1732549 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.7741. Min Act: -0.1700
Data Index: 1853314 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.8054. Min Act: -0.1700
Data Index: 6055405 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.8054. Min Act: -0.1700
Data Index: 2760700 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.8054. Min Act: -0.1700
Data Index: 2005050 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.7741. Min Act: -0.1700
Data Index: 8702546 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.6804. Min Act: -0.1700
Data Index: 3790226 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.6804. Min Act: -0.1700
Data Index: 3703232 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.6804. Min Act: -0.1700
Data Index: 8675980 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.6804. Min Act: -0.1700
Data Index: 1746405 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.6491. Min Act: -0.1700
Data Index: 3377655 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.6491. Min Act: -0.1700
Data Index: 3055998 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.6491. Min Act: -0.1700
Data Index: 2486340 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.6179. Min Act: -0.1700
Data Index: 7598488 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.6179. Min Act: -0.1700
Data Index: 1832280 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0866. Min Range: -5.0866
Max Act: 4.5866. Min Act: -0.1700
Data Index: 3089955 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19