Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1894 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.6095. Min Act: -0.1700
Data Index: 4329825 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6095. Min Range: -7.6095
Max Act: 7.5782. Min Act: -0.1700
Data Index: 982269 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.7032. Min Act: -0.1700
Data Index: 5242647 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.7032. Min Act: -0.1700
Data Index: 1466049 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.6095. Min Act: -0.1700
Data Index: 980211 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.6095. Min Act: -0.1700
Data Index: 7443557 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.5470. Min Act: -0.1700
Data Index: 834473 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.5782. Min Act: -0.1700
Data Index: 2386834 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.5782. Min Act: -0.1700
Data Index: 6329165 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.5470. Min Act: -0.1700
Data Index: 8625969 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.5470. Min Act: -0.1700
Data Index: 4218072 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.5157. Min Act: -0.1700
Data Index: 24045 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.5157. Min Act: -0.1700
Data Index: 6478259 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.4845. Min Act: -0.1700
Data Index: 8681115 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.4845. Min Act: -0.1700
Data Index: 7026370 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.4845. Min Act: -0.1700
Data Index: 7548517 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.4845. Min Act: -0.1700
Data Index: 4218067 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.4845. Min Act: -0.1700
Data Index: 5424083 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.4845. Min Act: -0.1700
Data Index: 969165 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6095. Min Range: -7.6095
Max Act: 6.4532. Min Act: -0.1700
Data Index: 2011836 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19