Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2839 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2011. Min Range: -6.2011
Max Act: 6.2011. Min Act: -0.1700
Data Index: 8336166 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2011. Min Range: -6.2011
Max Act: 6.1699. Min Act: -0.1700
Data Index: 5088408 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2011. Min Range: -6.2011
Max Act: 6.0449. Min Act: -0.1700
Data Index: 2590766 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.8886. Min Act: -0.1700
Data Index: 3586188 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.7949. Min Act: -0.1700
Data Index: 7672155 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.7324. Min Act: -0.1700
Data Index: 3656431 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.7324. Min Act: -0.1700
Data Index: 573700 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.7636. Min Act: -0.1700
Data Index: 8238071 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.7324. Min Act: -0.1700
Data Index: 8689615 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.7324. Min Act: -0.1700
Data Index: 3962564 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.7011. Min Act: -0.1700
Data Index: 6928640 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.6386. Min Act: -0.1700
Data Index: 1099363 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.6386. Min Act: -0.1700
Data Index: 6154479 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.6074. Min Act: -0.1700
Data Index: 1924568 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.6074. Min Act: -0.1700
Data Index: 4533314 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.6074. Min Act: -0.1700
Data Index: 8109845 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.6074. Min Act: -0.1700
Data Index: 2586921 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.5761. Min Act: -0.1700
Data Index: 2207675 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.5761. Min Act: -0.1700
Data Index: 3032238 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2011. Min Range: -6.2011
Max Act: 5.5761. Min Act: -0.1700
Data Index: 3921257 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19