Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1496 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.7300. Min Act: -0.1700
Data Index: 1743566 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.2925. Min Act: -0.1700
Data Index: 5991461 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.2925. Min Act: -0.1700
Data Index: 1999216 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.2612. Min Act: -0.1700
Data Index: 1342238 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.2300. Min Act: -0.1700
Data Index: 2345467 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.1987. Min Act: -0.1700
Data Index: 4278028 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.1675. Min Act: -0.1700
Data Index: 2751136 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.1675. Min Act: -0.1700
Data Index: 6136391 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.1675. Min Act: -0.1700
Data Index: 1846652 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.1362. Min Act: -0.1700
Data Index: 4768110 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.1362. Min Act: -0.1700
Data Index: 3384068 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.1050. Min Act: -0.1700
Data Index: 5936032 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.1050. Min Act: -0.1700
Data Index: 1987493 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.0737. Min Act: -0.1700
Data Index: 3434258 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.0737. Min Act: -0.1700
Data Index: 906811 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.0737. Min Act: -0.1700
Data Index: 6560268 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.0737. Min Act: -0.1700
Data Index: 8253210 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.0425. Min Act: -0.1700
Data Index: 2920112 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.0425. Min Act: -0.1700
Data Index: 347213 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7300. Min Range: -6.7300
Max Act: 6.0112. Min Act: -0.1700
Data Index: 2508784 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19