Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3547 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.5908. Min Act: -0.1700
Data Index: 497026 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.5595. Min Act: -0.1700
Data Index: 5261904 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.4970. Min Act: -0.1700
Data Index: 8296700 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.4658. Min Act: -0.1700
Data Index: 5404410 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.4033. Min Act: -0.1700
Data Index: 2390720 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.4033. Min Act: -0.1700
Data Index: 8474470 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.4033. Min Act: -0.1700
Data Index: 5567183 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.3720. Min Act: -0.1700
Data Index: 4413932 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.3720. Min Act: -0.1700
Data Index: 5007418 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.3720. Min Act: -0.1700
Data Index: 4852774 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.3095. Min Act: -0.1700
Data Index: 8270246 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.3095. Min Act: -0.1700
Data Index: 17473 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.3095. Min Act: -0.1700
Data Index: 905208 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.3095. Min Act: -0.1700
Data Index: 199385 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.3095. Min Act: -0.1700
Data Index: 8470650 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.2783. Min Act: -0.1700
Data Index: 869453 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.2783. Min Act: -0.1700
Data Index: 1848553 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.2470. Min Act: -0.1700
Data Index: 2880658 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.2158. Min Act: -0.1700
Data Index: 1235592 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5908. Min Range: -5.5908
Max Act: 5.1845. Min Act: -0.1700
Data Index: 7924878 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19