Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3630 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.5820. Min Act: -0.1700
Data Index: 7094705 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.4570. Min Act: -0.1700
Data Index: 6299235 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.4257. Min Act: -0.1700
Data Index: 6463783 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3945. Min Act: -0.1700
Data Index: 494728 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3945. Min Act: -0.1700
Data Index: 215210 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3945. Min Act: -0.1700
Data Index: 1135234 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3945. Min Act: -0.1700
Data Index: 4502822 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3945. Min Act: -0.1700
Data Index: 7154180 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 7992163 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 1273621 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 4490520 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 552323 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 7351321 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 2699261 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 921953 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 1889897 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 1432577 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3007. Min Act: -0.1700
Data Index: 7154181 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3007. Min Act: -0.1700
Data Index: 3505376 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5820. Min Range: -5.5820
Max Act: 5.3320. Min Act: -0.1700
Data Index: 6176831 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19