Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6363 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.5407. Min Act: -0.1700
Data Index: 2545540 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.4470. Min Act: -0.1700
Data Index: 7420802 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.3845. Min Act: -0.1700
Data Index: 3550386 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.3845. Min Act: -0.1700
Data Index: 2755675 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.3532. Min Act: -0.1700
Data Index: 3518681 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.2907. Min Act: -0.1700
Data Index: 2346115 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.2907. Min Act: -0.1700
Data Index: 635334 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.2595. Min Act: -0.1700
Data Index: 1133369 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.2595. Min Act: -0.1700
Data Index: 16494 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.2595. Min Act: -0.1700
Data Index: 8509631 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.2282. Min Act: -0.1700
Data Index: 8543054 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.2282. Min Act: -0.1700
Data Index: 4584695 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1970. Min Act: -0.1700
Data Index: 5641118 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1970. Min Act: -0.1700
Data Index: 635333 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1970. Min Act: -0.1700
Data Index: 4656668 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1970. Min Act: -0.1700
Data Index: 1458692 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1657. Min Act: -0.1700
Data Index: 6503069 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1657. Min Act: -0.1700
Data Index: 4900624 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1657. Min Act: -0.1700
Data Index: 3517492 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5407. Min Range: -7.5407
Max Act: 7.1032. Min Act: -0.1700
Data Index: 3033403 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #19