Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 775 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.2225. Min Act: -0.1700
Data Index: 7233410 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.2225. Min Act: -0.1700
Data Index: 3104204 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1561. Min Act: -0.1700
Data Index: 5369513 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1561. Min Act: -0.1700
Data Index: 7899046 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1561. Min Act: -0.1700
Data Index: 5369510 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1561. Min Act: -0.1700
Data Index: 7302917 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1394. Min Act: -0.1700
Data Index: 4424377 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1394. Min Act: -0.1700
Data Index: 5983604 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1394. Min Act: -0.1700
Data Index: 1848359 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1227. Min Act: -0.1700
Data Index: 478717 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1227. Min Act: -0.1700
Data Index: 5589130 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1227. Min Act: -0.1700
Data Index: 8688226 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1227. Min Act: -0.1700
Data Index: 3080350 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1227. Min Act: -0.1700
Data Index: 1587441 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1227. Min Act: -0.1700
Data Index: 3400675 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1060. Min Act: -0.1700
Data Index: 4116726 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1227. Min Act: -0.1700
Data Index: 5149242 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.1060. Min Act: -0.1700
Data Index: 3589161 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.0892. Min Act: -0.1700
Data Index: 1922135 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2225. Min Range: -2.2225
Max Act: 2.0892. Min Act: -0.1700
Data Index: 2241585 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19