Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 538 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.4169. Min Act: -0.1700
Data Index: 5230677 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.3856. Min Act: -0.1700
Data Index: 3911418 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.3544. Min Act: -0.1700
Data Index: 6040131 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.3544. Min Act: -0.1700
Data Index: 3443114 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.2294. Min Act: -0.1700
Data Index: 4694624 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.2294. Min Act: -0.1700
Data Index: 5754833 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.1981. Min Act: -0.1700
Data Index: 1267287 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.1981. Min Act: -0.1700
Data Index: 7684080 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.2294. Min Act: -0.1700
Data Index: 833637 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.1981. Min Act: -0.1700
Data Index: 159566 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.1981. Min Act: -0.1700
Data Index: 1502553 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.1669. Min Act: -0.1700
Data Index: 544601 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.1356. Min Act: -0.1700
Data Index: 3241385 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.1356. Min Act: -0.1700
Data Index: 734065 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.1356. Min Act: -0.1700
Data Index: 131865 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.0731. Min Act: -0.1700
Data Index: 7353582 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.1044. Min Act: -0.1700
Data Index: 4794388 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.1044. Min Act: -0.1700
Data Index: 4843494 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.1044. Min Act: -0.1700
Data Index: 2859487 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4169. Min Range: -6.4169
Max Act: 6.0731. Min Act: -0.1700
Data Index: 2801332 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #19