Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2951 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3493. Min Range: -5.3493
Max Act: 5.3493. Min Act: -0.1700
Data Index: 53952 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3493. Min Range: -5.3493
Max Act: 5.0993. Min Act: -0.1700
Data Index: 5844919 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3493. Min Range: -5.3493
Max Act: 5.1306. Min Act: -0.1700
Data Index: 2042573 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3493. Min Range: -5.3493
Max Act: 5.0681. Min Act: -0.1700
Data Index: 6326989 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3493. Min Range: -5.3493
Max Act: 5.0368. Min Act: -0.1700
Data Index: 83140 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3493. Min Range: -5.3493
Max Act: 5.0056. Min Act: -0.1700
Data Index: 2594092 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9743. Min Act: -0.1700
Data Index: 1483415 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3493. Min Range: -5.3493
Max Act: 5.0056. Min Act: -0.1700
Data Index: 3012433 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9743. Min Act: -0.1700
Data Index: 8177590 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9431. Min Act: -0.1700
Data Index: 8666071 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9743. Min Act: -0.1700
Data Index: 5797333 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9743. Min Act: -0.1700
Data Index: 1594836 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9431. Min Act: -0.1700
Data Index: 1059221 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9431. Min Act: -0.1700
Data Index: 993160 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9431. Min Act: -0.1700
Data Index: 2749376 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9431. Min Act: -0.1700
Data Index: 2642085 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9431. Min Act: -0.1700
Data Index: 1961660 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9431. Min Act: -0.1700
Data Index: 77336 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9431. Min Act: -0.1700
Data Index: 4442683 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3493. Min Range: -5.3493
Max Act: 4.9431. Min Act: -0.1700
Data Index: 3678690 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19