Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 443 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0125. Min Range: -7.0125
Max Act: 7.0125. Min Act: -0.1700
Data Index: 4016807 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.4812. Min Act: -0.1700
Data Index: 2563599 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.4500. Min Act: -0.1700
Data Index: 2625338 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.4500. Min Act: -0.1700
Data Index: 4235527 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.3875. Min Act: -0.1700
Data Index: 1352447 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.3562. Min Act: -0.1700
Data Index: 7857974 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.3250. Min Act: -0.1700
Data Index: 7184347 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.2937. Min Act: -0.1700
Data Index: 3159574 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.2937. Min Act: -0.1700
Data Index: 413158 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.2625. Min Act: -0.1700
Data Index: 3926057 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.2312. Min Act: -0.1700
Data Index: 1345923 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.2312. Min Act: -0.1700
Data Index: 8197722 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.2312. Min Act: -0.1700
Data Index: 2928795 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.2000. Min Act: -0.1700
Data Index: 7604802 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.1687. Min Act: -0.1700
Data Index: 2988768 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.1687. Min Act: -0.1700
Data Index: 4908829 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.1687. Min Act: -0.1700
Data Index: 2688231 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.1375. Min Act: -0.1700
Data Index: 3609449 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.1062. Min Act: -0.1700
Data Index: 5283108 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0125. Min Range: -7.0125
Max Act: 6.1062. Min Act: -0.1700
Data Index: 1226005 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19