Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 699 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.5073. Min Act: -0.1700
Data Index: 5685899 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.4098. Min Act: -0.1700
Data Index: 1505761 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.2787. Min Act: -0.1700
Data Index: 2223900 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.2787. Min Act: -0.1700
Data Index: 8481410 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.2622. Min Act: -0.1700
Data Index: 6393327 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.2622. Min Act: -0.1700
Data Index: 8637909 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.2457. Min Act: -0.1700
Data Index: 8023805 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.2291. Min Act: -0.1700
Data Index: 1663852 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.2291. Min Act: -0.1700
Data Index: 8757620 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.2126. Min Act: -0.1700
Data Index: 7452024 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.2291. Min Act: -0.1700
Data Index: 2958974 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.2126. Min Act: -0.1700
Data Index: 8409149 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.2126. Min Act: -0.1700
Data Index: 1186257 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.2126. Min Act: -0.1700
Data Index: 2666754 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.1960. Min Act: -0.1700
Data Index: 4805042 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.1960. Min Act: -0.1700
Data Index: 5298518 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.1960. Min Act: -0.1700
Data Index: 2890276 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.1960. Min Act: -0.1700
Data Index: 5936480 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.1793. Min Act: -0.1700
Data Index: 1141427 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5073. Min Range: -2.5073
Max Act: 2.1793. Min Act: -0.1700
Data Index: 2217775 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19