Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1831 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5161. Min Range: -7.5161
Max Act: 7.5161. Min Act: -0.1700
Data Index: 4800937 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5161. Min Range: -7.5161
Max Act: 7.0161. Min Act: -0.1700
Data Index: 3227837 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.7973. Min Act: -0.1700
Data Index: 295113 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.7661. Min Act: -0.1700
Data Index: 2565254 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5161. Min Range: -7.5161
Max Act: 7.1723. Min Act: -0.1700
Data Index: 2710561 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.6723. Min Act: -0.1700
Data Index: 6190912 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.7348. Min Act: -0.1700
Data Index: 5234711 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.6723. Min Act: -0.1700
Data Index: 5842203 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.7973. Min Act: -0.1700
Data Index: 2156879 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.7348. Min Act: -0.1700
Data Index: 6313311 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.6098. Min Act: -0.1700
Data Index: 8542749 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.5786. Min Act: -0.1700
Data Index: 5484861 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.5161. Min Act: -0.1700
Data Index: 4651323 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.6098. Min Act: -0.1700
Data Index: 6101446 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.7661. Min Act: -0.1700
Data Index: 5415224 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5161. Min Range: -7.5161
Max Act: 5.6723. Min Act: -0.1700
Data Index: 6160069 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.5161. Min Act: -0.1700
Data Index: 295111 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.2973. Min Act: -0.1700
Data Index: 3746706 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5161. Min Range: -7.5161
Max Act: 5.8911. Min Act: -0.1700
Data Index: 3384152 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5161. Min Range: -7.5161
Max Act: 6.5161. Min Act: -0.1700
Data Index: 295114 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19