Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6009 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.9101. Min Act: -0.1700
Data Index: 3422120 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.7226. Min Act: -0.1700
Data Index: 6168771 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.5351. Min Act: -0.1700
Data Index: 5136549 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.4101. Min Act: -0.1700
Data Index: 8615787 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.2851. Min Act: -0.1700
Data Index: 8284702 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.2851. Min Act: -0.1700
Data Index: 4355439 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.2226. Min Act: -0.1700
Data Index: 439602 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.1601. Min Act: -0.1700
Data Index: 7639211 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.1601. Min Act: -0.1700
Data Index: 5896598 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.0976. Min Act: -0.1700
Data Index: 6259844 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.0976. Min Act: -0.1700
Data Index: 5249922 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.0976. Min Act: -0.1700
Data Index: 754513 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9101. Min Range: -9.9101
Max Act: 9.0351. Min Act: -0.1700
Data Index: 8640935 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9101. Min Range: -9.9101
Max Act: 8.9726. Min Act: -0.1700
Data Index: 7623757 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9101. Min Range: -9.9101
Max Act: 8.9726. Min Act: -0.1700
Data Index: 4427053 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9101. Min Range: -9.9101
Max Act: 8.9726. Min Act: -0.1700
Data Index: 7451249 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9101. Min Range: -9.9101
Max Act: 8.9726. Min Act: -0.1700
Data Index: 8546504 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9101. Min Range: -9.9101
Max Act: 8.9726. Min Act: -0.1700
Data Index: 1533977 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9101. Min Range: -9.9101
Max Act: 8.9726. Min Act: -0.1700
Data Index: 7983553 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9101. Min Range: -9.9101
Max Act: 8.9101. Min Act: -0.1700
Data Index: 884598 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19