Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2891 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2957. Min Act: -0.1700
Data Index: 2577028 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2643. Min Act: -0.1700
Data Index: 7502276 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2643. Min Act: -0.1700
Data Index: 6816671 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2329. Min Act: -0.1700
Data Index: 8057843 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2329. Min Act: -0.1700
Data Index: 6878976 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2329. Min Act: -0.1700
Data Index: 703264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2329. Min Act: -0.1700
Data Index: 2153905 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2014. Min Act: -0.1700
Data Index: 1698600 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2014. Min Act: -0.1700
Data Index: 589352 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.1700. Min Act: -0.1700
Data Index: 1743374 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2014. Min Act: -0.1700
Data Index: 1285413 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2014. Min Act: -0.1700
Data Index: 5707956 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2014. Min Act: -0.1700
Data Index: 6268797 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2014. Min Act: -0.1700
Data Index: 182776 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2014. Min Act: -0.1700
Data Index: 4630781 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2014. Min Act: -0.1697
Data Index: 499542 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2014. Min Act: -0.1700
Data Index: 491488 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2014. Min Act: -0.1700
Data Index: 816108 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2014. Min Act: -0.1700
Data Index: 833942 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2957. Min Range: -3.2957
Max Act: 3.2014. Min Act: -0.1700
Data Index: 7374835 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19