Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1954 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4405. Min Range: -5.4405
Max Act: 5.4405. Min Act: -0.1700
Data Index: 878674 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4405. Min Range: -5.4405
Max Act: 5.1905. Min Act: -0.1700
Data Index: 4378503 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4405. Min Range: -5.4405
Max Act: 5.1593. Min Act: -0.1700
Data Index: 7372184 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4405. Min Range: -5.4405
Max Act: 5.0655. Min Act: -0.1700
Data Index: 344237 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4405. Min Range: -5.4405
Max Act: 5.0343. Min Act: -0.1700
Data Index: 8573904 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4405. Min Range: -5.4405
Max Act: 5.0030. Min Act: -0.1700
Data Index: 6867695 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.9718. Min Act: -0.1700
Data Index: 2800815 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.9718. Min Act: -0.1700
Data Index: 6241685 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.9718. Min Act: -0.1700
Data Index: 560850 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.9405. Min Act: -0.1700
Data Index: 1193019 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.9405. Min Act: -0.1700
Data Index: 7032985 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.9093. Min Act: -0.1700
Data Index: 5608906 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.9405. Min Act: -0.1700
Data Index: 3583055 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.8780. Min Act: -0.1700
Data Index: 3020001 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.9093. Min Act: -0.1700
Data Index: 8414094 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.9093. Min Act: -0.1700
Data Index: 3412243 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.8780. Min Act: -0.1700
Data Index: 2454951 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.9093. Min Act: -0.1700
Data Index: 5599693 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.8780. Min Act: -0.1700
Data Index: 6373074 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4405. Min Range: -5.4405
Max Act: 4.8468. Min Act: -0.1700
Data Index: 6953095 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #19