Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5175 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1206. Min Range: -8.1206
Max Act: 8.1206. Min Act: -0.1700
Data Index: 5535379 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.7456. Min Act: -0.1700
Data Index: 3011067 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.6206. Min Act: -0.1700
Data Index: 8796380 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.5893. Min Act: -0.1700
Data Index: 6360509 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.5893. Min Act: -0.1700
Data Index: 1417464 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.5893. Min Act: -0.1700
Data Index: 2903707 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.5581. Min Act: -0.1700
Data Index: 8213931 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.5581. Min Act: -0.1700
Data Index: 2594010 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.5581. Min Act: -0.1700
Data Index: 564445 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.5581. Min Act: -0.1700
Data Index: 6117756 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.5268. Min Act: -0.1700
Data Index: 1922052 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.5268. Min Act: -0.1700
Data Index: 5205338 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.5268. Min Act: -0.1700
Data Index: 1014294 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.4956. Min Act: -0.1700
Data Index: 5631107 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.4018. Min Act: -0.1700
Data Index: 1892753 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.4331. Min Act: -0.1700
Data Index: 1018053 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.4018. Min Act: -0.1700
Data Index: 2934746 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.3706. Min Act: -0.1700
Data Index: 5965121 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.4018. Min Act: -0.1700
Data Index: 789108 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1206. Min Range: -8.1206
Max Act: 7.3706. Min Act: -0.1700
Data Index: 4785194 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #19