Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4578 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2088. Min Range: -6.2088
Max Act: 6.2088. Min Act: -0.1700
Data Index: 2419938 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2088. Min Range: -6.2088
Max Act: 6.0526. Min Act: -0.1700
Data Index: 3851698 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2088. Min Range: -6.2088
Max Act: 6.0526. Min Act: -0.1700
Data Index: 6875897 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.9901. Min Act: -0.1700
Data Index: 265939 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.9901. Min Act: -0.1700
Data Index: 8724769 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.9588. Min Act: -0.1700
Data Index: 1280274 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.9588. Min Act: -0.1700
Data Index: 2403087 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.9276. Min Act: -0.1700
Data Index: 7494300 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.9276. Min Act: -0.1700
Data Index: 2599139 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.8963. Min Act: -0.1700
Data Index: 3758850 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.8963. Min Act: -0.1700
Data Index: 7280814 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.8963. Min Act: -0.1700
Data Index: 6773614 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.8651. Min Act: -0.1700
Data Index: 1040864 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.8651. Min Act: -0.1700
Data Index: 846478 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.8651. Min Act: -0.1700
Data Index: 1809880 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.8651. Min Act: -0.1700
Data Index: 995767 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.8651. Min Act: -0.1700
Data Index: 6741350 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.8338. Min Act: -0.1700
Data Index: 6854714 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.8338. Min Act: -0.1700
Data Index: 7059371 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2088. Min Range: -6.2088
Max Act: 5.8338. Min Act: -0.1700
Data Index: 6725492 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19