Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3088 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1897. Min Range: -6.1897
Max Act: 6.1897. Min Act: -0.1700
Data Index: 5875400 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1897. Min Range: -6.1897
Max Act: 6.0647. Min Act: -0.1700
Data Index: 7382337 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.9710. Min Act: -0.1700
Data Index: 7862455 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.9710. Min Act: -0.1700
Data Index: 4494258 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.9710. Min Act: -0.1700
Data Index: 434417 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.9397. Min Act: -0.1700
Data Index: 6996199 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.9085. Min Act: -0.1700
Data Index: 5181178 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.9085. Min Act: -0.1700
Data Index: 5875401 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.9085. Min Act: -0.1700
Data Index: 4904111 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.8460. Min Act: -0.1700
Data Index: 295880 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.8460. Min Act: -0.1700
Data Index: 4792878 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.8147. Min Act: -0.1700
Data Index: 2147838 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.8147. Min Act: -0.1700
Data Index: 5957055 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.7835. Min Act: -0.1700
Data Index: 5303516 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.7835. Min Act: -0.1700
Data Index: 6116998 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.7835. Min Act: -0.1700
Data Index: 1532786 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.7522. Min Act: -0.1700
Data Index: 3477983 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.7835. Min Act: -0.1700
Data Index: 2497273 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.7835. Min Act: -0.1700
Data Index: 501824 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1897. Min Range: -6.1897
Max Act: 5.7522. Min Act: -0.1700
Data Index: 3775699 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19