Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3255. Min Range: -7.3255
Max Act: 7.3255. Min Act: -0.1700
Data Index: 7460553 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3255. Min Range: -7.3255
Max Act: 7.2005. Min Act: -0.1700
Data Index: 6169393 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3255. Min Range: -7.3255
Max Act: 7.0442. Min Act: -0.1700
Data Index: 2278769 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.8880. Min Act: -0.1700
Data Index: 5651940 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.8255. Min Act: -0.1700
Data Index: 2192461 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.7942. Min Act: -0.1700
Data Index: 5782957 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.7630. Min Act: -0.1700
Data Index: 7045236 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.7317. Min Act: -0.1700
Data Index: 5008394 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.7005. Min Act: -0.1700
Data Index: 534046 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.6692. Min Act: -0.1700
Data Index: 6122591 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.6380. Min Act: -0.1700
Data Index: 1637005 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.6380. Min Act: -0.1700
Data Index: 2918253 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.6380. Min Act: -0.1700
Data Index: 1780148 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.6067. Min Act: -0.1700
Data Index: 8329761 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.6067. Min Act: -0.1700
Data Index: 200781 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.5755. Min Act: -0.1700
Data Index: 7454345 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.5755. Min Act: -0.1700
Data Index: 1521278 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.5755. Min Act: -0.1700
Data Index: 6875484 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.5442. Min Act: -0.1700
Data Index: 6795325 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3255. Min Range: -7.3255
Max Act: 6.5442. Min Act: -0.1700
Data Index: 187980 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19