Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2676 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.1060. Min Act: -0.1700
Data Index: 452604 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.1060. Min Act: -0.1700
Data Index: 6501335 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0747. Min Act: -0.1700
Data Index: 4060162 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0747. Min Act: -0.1700
Data Index: 4196107 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0747. Min Act: -0.1700
Data Index: 1087616 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0747. Min Act: -0.1700
Data Index: 7153788 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0434. Min Act: -0.1700
Data Index: 762940 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0434. Min Act: -0.1700
Data Index: 7897972 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0434. Min Act: -0.1700
Data Index: 7771526 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0434. Min Act: -0.1700
Data Index: 7425374 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0434. Min Act: -0.1700
Data Index: 7244702 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0434. Min Act: -0.1700
Data Index: 3067535 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0434. Min Act: -0.1700
Data Index: 2833716 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0434. Min Act: -0.1700
Data Index: 6433892 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0122. Min Act: -0.1700
Data Index: 5844151 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0434. Min Act: -0.1700
Data Index: 5790989 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0434. Min Act: -0.1700
Data Index: 4213612 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0434. Min Act: -0.1700
Data Index: 4110008 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0434. Min Act: -0.1700
Data Index: 1811273 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1060. Min Range: -4.1060
Max Act: 4.0122. Min Act: -0.1700
Data Index: 1551016 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #19