Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4080 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.6587. Min Act: -0.1700
Data Index: 1562869 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.6587. Min Act: -0.1700
Data Index: 5234312 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.6266. Min Act: -0.1700
Data Index: 8523800 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.5460. Min Act: -0.1700
Data Index: 6315624 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.5299. Min Act: -0.1700
Data Index: 8690122 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.5299. Min Act: -0.1700
Data Index: 7397996 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.5137. Min Act: -0.1700
Data Index: 4162609 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.5137. Min Act: -0.1700
Data Index: 990376 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.5137. Min Act: -0.1700
Data Index: 8770363 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.4975. Min Act: -0.1700
Data Index: 6315618 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.4651. Min Act: -0.1700
Data Index: 655024 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.4975. Min Act: -0.1700
Data Index: 3645579 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.4651. Min Act: -0.1700
Data Index: 7397998 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.4651. Min Act: -0.1700
Data Index: 1637272 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.4651. Min Act: -0.1700
Data Index: 3645580 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.4651. Min Act: -0.1700
Data Index: 6315621 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.4651. Min Act: -0.1700
Data Index: 5412530 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.4488. Min Act: -0.1700
Data Index: 7870961 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.4488. Min Act: -0.1700
Data Index: 3797334 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6587. Min Range: -2.6587
Max Act: 2.4488. Min Act: -0.1700
Data Index: 6315623 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19