Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6346 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.7198. Min Act: -0.1700
Data Index: 4326746 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4386. Min Act: -0.1700
Data Index: 4008137 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.4386. Min Act: -0.1700
Data Index: 4326748 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3761. Min Act: -0.1700
Data Index: 6883388 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3761. Min Act: -0.1700
Data Index: 6631070 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3448. Min Act: -0.1700
Data Index: 731265 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.3136. Min Act: -0.1700
Data Index: 8811621 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.2511. Min Act: -0.1700
Data Index: 7883542 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.2511. Min Act: -0.1700
Data Index: 1338858 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.1573. Min Act: -0.1700
Data Index: 1867407 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.1261. Min Act: -0.1700
Data Index: 4764053 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.1573. Min Act: -0.1700
Data Index: 3641278 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.1261. Min Act: -0.1700
Data Index: 8411486 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.1261. Min Act: -0.1700
Data Index: 8029237 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.1261. Min Act: -0.1700
Data Index: 5627829 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.0948. Min Act: -0.1700
Data Index: 25925 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.0948. Min Act: -0.1700
Data Index: 759762 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.0948. Min Act: -0.1700
Data Index: 4659774 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.1261. Min Act: -0.1700
Data Index: 8527381 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7198. Min Range: -5.7198
Max Act: 5.0636. Min Act: -0.1700
Data Index: 5013508 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19