Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1636 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.1497. Min Act: -0.1700
Data Index: 5835038 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.1497. Min Act: -0.1700
Data Index: 550080 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.1497. Min Act: -0.1700
Data Index: 3360819 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.1184. Min Act: -0.1700
Data Index: 3068524 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.1184. Min Act: -0.1700
Data Index: 8603495 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.0872. Min Act: -0.1700
Data Index: 1336275 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.0872. Min Act: -0.1700
Data Index: 6120672 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.0872. Min Act: -0.1700
Data Index: 3304817 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.0872. Min Act: -0.1700
Data Index: 6716044 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.0872. Min Act: -0.1700
Data Index: 4735523 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.0559. Min Act: -0.1700
Data Index: 4111899 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.0247. Min Act: -0.1700
Data Index: 3802649 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.9934. Min Act: -0.1700
Data Index: 1205779 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.9934. Min Act: -0.1700
Data Index: 699480 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.9934. Min Act: -0.1699
Data Index: 7643871 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1497. Min Range: -5.1497
Max Act: 5.0247. Min Act: -0.1700
Data Index: 5035546 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.9934. Min Act: -0.1700
Data Index: 1205782 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.9934. Min Act: -0.1700
Data Index: 4014480 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.9622. Min Act: -0.1700
Data Index: 5700007 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1497. Min Range: -5.1497
Max Act: 4.9622. Min Act: -0.1700
Data Index: 5835040 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19