Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3334 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.7528. Min Act: -0.1700
Data Index: 6885080 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.6835. Min Act: -0.1700
Data Index: 1867580 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.6313. Min Act: -0.1700
Data Index: 4656379 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.6139. Min Act: -0.1700
Data Index: 599254 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5964. Min Act: -0.1700
Data Index: 1602732 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5790. Min Act: -0.1700
Data Index: 8249904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5790. Min Act: -0.1700
Data Index: 4284866 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5615. Min Act: -0.1700
Data Index: 5740407 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5615. Min Act: -0.1700
Data Index: 4257645 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5615. Min Act: -0.1700
Data Index: 4683962 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5264. Min Act: -0.1700
Data Index: 2039550 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5264. Min Act: -0.1700
Data Index: 8794517 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5352. Min Act: -0.1700
Data Index: 3265778 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5352. Min Act: -0.1700
Data Index: 2843603 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5176. Min Act: -0.1700
Data Index: 3094831 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5176. Min Act: -0.1700
Data Index: 2565124 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5176. Min Act: -0.1699
Data Index: 2589979 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5001. Min Act: -0.1700
Data Index: 6851586 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5089. Min Act: -0.1699
Data Index: 2406952 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7528. Min Range: -1.7528
Max Act: 1.5089. Min Act: -0.1700
Data Index: 7385251 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19