Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2224 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.6543. Min Act: -0.1700
Data Index: 3354680 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.6383. Min Act: -0.1700
Data Index: 7313068 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.6383. Min Act: -0.1700
Data Index: 5224968 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.5900. Min Act: -0.1700
Data Index: 6288778 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.6061. Min Act: -0.1700
Data Index: 3250243 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.5739. Min Act: -0.1700
Data Index: 6390472 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.5578. Min Act: -0.1700
Data Index: 5547388 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.5578. Min Act: -0.1700
Data Index: 6942841 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.5255. Min Act: -0.1700
Data Index: 3857091 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.5416. Min Act: -0.1700
Data Index: 303637 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.5416. Min Act: -0.1700
Data Index: 8441067 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.5255. Min Act: -0.1700
Data Index: 4123825 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.5093. Min Act: -0.1700
Data Index: 3425025 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.5093. Min Act: -0.1700
Data Index: 3754381 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.4931. Min Act: -0.1700
Data Index: 4544322 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.4769. Min Act: -0.1700
Data Index: 5106162 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.4769. Min Act: -0.1700
Data Index: 1466411 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.4769. Min Act: -0.1700
Data Index: 6449501 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.4769. Min Act: -0.1700
Data Index: 4045865 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6543. Min Range: -2.6543
Max Act: 2.4769. Min Act: -0.1700
Data Index: 5408026 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19