Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1148 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.7774. Min Act: -0.1700
Data Index: 6215246 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.7149. Min Act: -0.1700
Data Index: 2983818 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.6524. Min Act: -0.1700
Data Index: 4946903 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.6524. Min Act: -0.1700
Data Index: 2057924 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.6212. Min Act: -0.1700
Data Index: 4343631 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.6212. Min Act: -0.1700
Data Index: 6729770 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.6212. Min Act: -0.1700
Data Index: 3448645 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.6212. Min Act: -0.1700
Data Index: 1752399 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.6212. Min Act: -0.1700
Data Index: 2820082 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.5899. Min Act: -0.1700
Data Index: 258403 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.5899. Min Act: -0.1700
Data Index: 5678791 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.5899. Min Act: -0.1700
Data Index: 1701575 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.5899. Min Act: -0.1700
Data Index: 560415 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.5899. Min Act: -0.1700
Data Index: 1594614 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.5587. Min Act: -0.1700
Data Index: 5126786 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.5587. Min Act: -0.1700
Data Index: 4692970 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.5587. Min Act: -0.1700
Data Index: 278970 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.5587. Min Act: -0.1700
Data Index: 4400250 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.5587. Min Act: -0.1700
Data Index: 4101634 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7774. Min Range: -4.7774
Max Act: 4.5587. Min Act: -0.1700
Data Index: 5043216 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19