Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2193 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.4510. Min Act: -0.1700
Data Index: 7659398 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.3885. Min Act: -0.1700
Data Index: 2774817 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.3260. Min Act: -0.1700
Data Index: 2570386 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.3260. Min Act: -0.1700
Data Index: 5654542 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.2010. Min Act: -0.1700
Data Index: 4889670 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.2010. Min Act: -0.1700
Data Index: 4060796 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.1385. Min Act: -0.1700
Data Index: 5775413 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.1385. Min Act: -0.1700
Data Index: 7931065 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.1385. Min Act: -0.1700
Data Index: 873285 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.0760. Min Act: -0.1700
Data Index: 6804953 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.1385. Min Act: -0.1700
Data Index: 745611 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.1385. Min Act: -0.1700
Data Index: 4130582 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.0760. Min Act: -0.1700
Data Index: 2630409 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.0760. Min Act: -0.1700
Data Index: 5592936 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.0760. Min Act: -0.1700
Data Index: 2073083 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.0760. Min Act: -0.1700
Data Index: 3031472 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.0760. Min Act: -0.1700
Data Index: 6445402 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.0760. Min Act: -0.1700
Data Index: 4280416 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.0760. Min Act: -0.1700
Data Index: 501245 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4510. Min Range: -8.4510
Max Act: 8.0135. Min Act: -0.1700
Data Index: 6087685 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19