Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3361 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2625. Min Range: -5.2625
Max Act: 5.2625. Min Act: -0.1700
Data Index: 7572621 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2625. Min Range: -5.2625
Max Act: 5.2625. Min Act: -0.1700
Data Index: 4033070 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2625. Min Range: -5.2625
Max Act: 5.1375. Min Act: -0.1700
Data Index: 5700897 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2625. Min Range: -5.2625
Max Act: 5.1062. Min Act: -0.1700
Data Index: 6370510 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2625. Min Range: -5.2625
Max Act: 5.0437. Min Act: -0.1700
Data Index: 6964671 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.9500. Min Act: -0.1700
Data Index: 232870 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.9500. Min Act: -0.1700
Data Index: 3330792 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.8562. Min Act: -0.1700
Data Index: 4948938 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.8250. Min Act: -0.1700
Data Index: 6271258 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.8250. Min Act: -0.1700
Data Index: 8247577 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.7625. Min Act: -0.1700
Data Index: 248568 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.7625. Min Act: -0.1700
Data Index: 6499955 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.7312. Min Act: -0.1700
Data Index: 4526384 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.7000. Min Act: -0.1700
Data Index: 3396173 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.7000. Min Act: -0.1700
Data Index: 7124001 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.7000. Min Act: -0.1700
Data Index: 786298 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.6687. Min Act: -0.1700
Data Index: 4255155 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.6375. Min Act: -0.1700
Data Index: 215161 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.6375. Min Act: -0.1700
Data Index: 4076842 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2625. Min Range: -5.2625
Max Act: 4.6687. Min Act: -0.1700
Data Index: 4846396 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19