Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3238 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5473. Min Range: -6.5473
Max Act: 6.5473. Min Act: -0.1700
Data Index: 7098808 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5473. Min Range: -6.5473
Max Act: 6.2036. Min Act: -0.1700
Data Index: 563932 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5473. Min Range: -6.5473
Max Act: 6.2036. Min Act: -0.1700
Data Index: 7209479 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5473. Min Range: -6.5473
Max Act: 6.1411. Min Act: -0.1700
Data Index: 5452652 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5473. Min Range: -6.5473
Max Act: 6.1098. Min Act: -0.1700
Data Index: 6761285 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5473. Min Range: -6.5473
Max Act: 6.0786. Min Act: -0.1700
Data Index: 7913340 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5473. Min Range: -6.5473
Max Act: 6.0786. Min Act: -0.1700
Data Index: 2709931 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5473. Min Range: -6.5473
Max Act: 6.0161. Min Act: -0.1700
Data Index: 1136930 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5473. Min Range: -6.5473
Max Act: 6.0161. Min Act: -0.1700
Data Index: 8176221 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5473. Min Range: -6.5473
Max Act: 5.9223. Min Act: -0.1700
Data Index: 8346965 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5473. Min Range: -6.5473
Max Act: 5.9223. Min Act: -0.1700
Data Index: 4949310 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5473. Min Range: -6.5473
Max Act: 5.8911. Min Act: -0.1700
Data Index: 1244051 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5473. Min Range: -6.5473
Max Act: 5.8598. Min Act: -0.1700
Data Index: 7104679 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5473. Min Range: -6.5473
Max Act: 5.8286. Min Act: -0.1700
Data Index: 7976251 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5473. Min Range: -6.5473
Max Act: 5.7661. Min Act: -0.1700
Data Index: 4290726 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5473. Min Range: -6.5473
Max Act: 5.7973. Min Act: -0.1700
Data Index: 3448847 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5473. Min Range: -6.5473
Max Act: 5.7973. Min Act: -0.1700
Data Index: 1255515 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5473. Min Range: -6.5473
Max Act: 5.7661. Min Act: -0.1700
Data Index: 5964364 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5473. Min Range: -6.5473
Max Act: 5.7348. Min Act: -0.1700
Data Index: 2935939 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5473. Min Range: -6.5473
Max Act: 5.7661. Min Act: -0.1700
Data Index: 4312780 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19