Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4440 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3883. Min Range: -6.3883
Max Act: 6.3883. Min Act: -0.1700
Data Index: 4992068 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.8258. Min Act: -0.1700
Data Index: 5137582 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.7008. Min Act: -0.1700
Data Index: 4815908 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.6383. Min Act: -0.1700
Data Index: 5041327 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.6070. Min Act: -0.1700
Data Index: 356437 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.5758. Min Act: -0.1700
Data Index: 4697883 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.6070. Min Act: -0.1700
Data Index: 6019438 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.5758. Min Act: -0.1700
Data Index: 763831 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.5758. Min Act: -0.1700
Data Index: 4272935 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.5445. Min Act: -0.1700
Data Index: 3804453 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.5133. Min Act: -0.1700
Data Index: 5055018 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.5133. Min Act: -0.1700
Data Index: 6063704 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.5133. Min Act: -0.1700
Data Index: 2308553 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.4820. Min Act: -0.1700
Data Index: 5184282 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.4820. Min Act: -0.1700
Data Index: 7775508 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.4820. Min Act: -0.1700
Data Index: 3218966 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.4508. Min Act: -0.1700
Data Index: 1875102 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.4508. Min Act: -0.1700
Data Index: 6099342 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.4508. Min Act: -0.1700
Data Index: 1998400 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3883. Min Range: -6.3883
Max Act: 5.4508. Min Act: -0.1700
Data Index: 455805 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19