Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3817 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.5320. Min Act: -0.1700
Data Index: 7377091 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.5320. Min Act: -0.1700
Data Index: 5203971 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.5320. Min Act: -0.1700
Data Index: 4311374 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.5320. Min Act: -0.1700
Data Index: 7681117 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.5320. Min Act: -0.1700
Data Index: 741742 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.5320. Min Act: -0.1700
Data Index: 3325078 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.5320. Min Act: -0.1700
Data Index: 4152212 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.5320. Min Act: -0.1700
Data Index: 3309904 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.4694. Min Act: -0.1700
Data Index: 947444 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.4381. Min Act: -0.1700
Data Index: 2296124 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.4381. Min Act: -0.1700
Data Index: 4161501 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.4381. Min Act: -0.1700
Data Index: 7784772 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.5007. Min Act: -0.1700
Data Index: 6050204 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.4381. Min Act: -0.1700
Data Index: 2163187 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.4694. Min Act: -0.1700
Data Index: 7681118 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.4381. Min Act: -0.1700
Data Index: 6990029 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.4694. Min Act: -0.1700
Data Index: 6125253 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.4381. Min Act: -0.1700
Data Index: 920437 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.4224. Min Act: -0.1700
Data Index: 3248304 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5320. Min Range: -3.5320
Max Act: 3.4067. Min Act: -0.1700
Data Index: 6566936 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19