Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3432 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.2831. Min Range: -8.2831
Max Act: 8.2831. Min Act: -0.1700
Data Index: 8571242 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2831. Min Range: -8.2831
Max Act: 8.0956. Min Act: -0.1700
Data Index: 8294744 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.9706. Min Act: -0.1700
Data Index: 4896422 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.9706. Min Act: -0.1700
Data Index: 7089182 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2831. Min Range: -8.2831
Max Act: 8.0331. Min Act: -0.1700
Data Index: 1341337 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.9706. Min Act: -0.1700
Data Index: 2864904 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2831. Min Range: -8.2831
Max Act: 8.0331. Min Act: -0.1693
Data Index: 1511720 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.9706. Min Act: -0.1698
Data Index: 951092 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.9706. Min Act: -0.1700
Data Index: 6307192 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.9706. Min Act: -0.1700
Data Index: 4365492 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.9081. Min Act: -0.1700
Data Index: 8818121 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.8456. Min Act: -0.1700
Data Index: 8039850 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.9081. Min Act: -0.1697
Data Index: 135606 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.9081. Min Act: -0.1700
Data Index: 3734449 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.7831. Min Act: -0.1700
Data Index: 7980098 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.8456. Min Act: -0.1700
Data Index: 4026716 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.8456. Min Act: -0.1700
Data Index: 8663586 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.8456. Min Act: -0.1695
Data Index: 8295804 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.7831. Min Act: -0.1700
Data Index: 5317394 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2831. Min Range: -8.2831
Max Act: 7.7831. Min Act: -0.1700
Data Index: 2844846 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19