Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3511 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.4030. Min Act: -0.1700
Data Index: 1450118 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.4030. Min Act: -0.1700
Data Index: 4317738 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.3405. Min Act: -0.1700
Data Index: 2845205 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.3093. Min Act: -0.1700
Data Index: 2854109 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.2780. Min Act: -0.1700
Data Index: 3821002 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.2780. Min Act: -0.1700
Data Index: 4906014 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.2155. Min Act: -0.1700
Data Index: 5409339 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.2468. Min Act: -0.1700
Data Index: 490849 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.2468. Min Act: -0.1700
Data Index: 7966945 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.2155. Min Act: -0.1700
Data Index: 7197637 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.2155. Min Act: -0.1700
Data Index: 3287639 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.2155. Min Act: -0.1700
Data Index: 8566697 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.1843. Min Act: -0.1700
Data Index: 976322 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.2155. Min Act: -0.1700
Data Index: 4236875 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.1843. Min Act: -0.1700
Data Index: 574944 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.1843. Min Act: -0.1700
Data Index: 6140086 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.2155. Min Act: -0.1700
Data Index: 6098430 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.1530. Min Act: -0.1700
Data Index: 7007196 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.1530. Min Act: -0.1700
Data Index: 196945 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4030. Min Range: -6.4030
Max Act: 6.1218. Min Act: -0.1700
Data Index: 4702934 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #19