Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5289 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.5820. Min Act: -0.1700
Data Index: 4101367 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.5820. Min Act: -0.1700
Data Index: 3301115 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.4570. Min Act: -0.1700
Data Index: 2470888 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.4570. Min Act: -0.1700
Data Index: 5910372 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.4570. Min Act: -0.1700
Data Index: 2060812 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.4570. Min Act: -0.1700
Data Index: 2470887 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.3945. Min Act: -0.1700
Data Index: 582805 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.3320. Min Act: -0.1700
Data Index: 6154700 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.3945. Min Act: -0.1700
Data Index: 2504194 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.3320. Min Act: -0.1700
Data Index: 3789606 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.3008. Min Act: -0.1700
Data Index: 1406428 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.2695. Min Act: -0.1700
Data Index: 1935057 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.2383. Min Act: -0.1700
Data Index: 4336844 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.2383. Min Act: -0.1700
Data Index: 2287404 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.2383. Min Act: -0.1700
Data Index: 6989376 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.2070. Min Act: -0.1700
Data Index: 2663087 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.2070. Min Act: -0.1700
Data Index: 2287407 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.1758. Min Act: -0.1700
Data Index: 7272501 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.1758. Min Act: -0.1700
Data Index: 1046332 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5820. Min Range: -8.5820
Max Act: 8.1133. Min Act: -0.1700
Data Index: 6926100 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19