Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1815 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1208. Min Range: -7.1208
Max Act: 7.1208. Min Act: -0.1700
Data Index: 738028 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1208. Min Range: -7.1208
Max Act: 7.0271. Min Act: -0.1700
Data Index: 6512525 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.9333. Min Act: -0.1700
Data Index: 303482 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.9021. Min Act: -0.1700
Data Index: 709111 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.8083. Min Act: -0.1700
Data Index: 2452803 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.7146. Min Act: -0.1700
Data Index: 32118 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.7146. Min Act: -0.1700
Data Index: 6848716 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.7146. Min Act: -0.1700
Data Index: 1768351 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.6521. Min Act: -0.1700
Data Index: 6932504 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.5896. Min Act: -0.1700
Data Index: 5153863 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.5896. Min Act: -0.1700
Data Index: 2067949 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.5271. Min Act: -0.1700
Data Index: 2992297 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.4958. Min Act: -0.1700
Data Index: 5005388 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.4958. Min Act: -0.1700
Data Index: 4916838 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.4333. Min Act: -0.1700
Data Index: 2405908 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.4021. Min Act: -0.1700
Data Index: 5974158 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.4021. Min Act: -0.1700
Data Index: 2727884 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.3396. Min Act: -0.1700
Data Index: 5961143 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.3708. Min Act: -0.1700
Data Index: 6383384 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1208. Min Range: -7.1208
Max Act: 6.3708. Min Act: -0.1700
Data Index: 2808623 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19