Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4001 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.6081. Min Act: -0.1700
Data Index: 858802 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.4206. Min Act: -0.1700
Data Index: 2491952 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2956. Min Act: -0.1700
Data Index: 3196274 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2643. Min Act: -0.1700
Data Index: 4993565 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2018. Min Act: -0.1700
Data Index: 3922805 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.2018. Min Act: -0.1700
Data Index: 5179364 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.1393. Min Act: -0.1700
Data Index: 5179365 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.1706. Min Act: -0.1700
Data Index: 4975857 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.1393. Min Act: -0.1700
Data Index: 4821747 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.0455. Min Act: -0.1700
Data Index: 7789704 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.0455. Min Act: -0.1700
Data Index: 4821746 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.0455. Min Act: -0.1700
Data Index: 2692062 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.0455. Min Act: -0.1700
Data Index: 1223484 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.0143. Min Act: -0.1700
Data Index: 7072514 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.0143. Min Act: -0.1700
Data Index: 6059809 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6081. Min Range: -4.6081
Max Act: 4.0143. Min Act: -0.1700
Data Index: 2423417 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6081. Min Range: -4.6081
Max Act: 3.9830. Min Act: -0.1700
Data Index: 3874371 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6081. Min Range: -4.6081
Max Act: 3.9830. Min Act: -0.1700
Data Index: 2018812 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6081. Min Range: -4.6081
Max Act: 3.9830. Min Act: -0.1700
Data Index: 544443 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6081. Min Range: -4.6081
Max Act: 3.9830. Min Act: -0.1700
Data Index: 456246 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19