Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3058 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1959. Min Range: -7.1959
Max Act: 7.1959. Min Act: -0.1700
Data Index: 5828844 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.9459. Min Act: -0.1700
Data Index: 1117071 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.8834. Min Act: -0.1700
Data Index: 8795443 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.8522. Min Act: -0.1700
Data Index: 4935888 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.8834. Min Act: -0.1700
Data Index: 7876802 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.8522. Min Act: -0.1700
Data Index: 2009559 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.8209. Min Act: -0.1700
Data Index: 7957138 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.8209. Min Act: -0.1700
Data Index: 1460790 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.7897. Min Act: -0.1700
Data Index: 954363 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.7584. Min Act: -0.1700
Data Index: 6615332 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.7584. Min Act: -0.1700
Data Index: 1632415 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.7897. Min Act: -0.1700
Data Index: 8145516 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.7272. Min Act: -0.1700
Data Index: 6653746 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.7272. Min Act: -0.1700
Data Index: 19016 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.7272. Min Act: -0.1700
Data Index: 7982293 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.6959. Min Act: -0.1700
Data Index: 7235534 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.6959. Min Act: -0.1700
Data Index: 8761486 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.6959. Min Act: -0.1700
Data Index: 804153 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.6647. Min Act: -0.1700
Data Index: 8784796 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1959. Min Range: -7.1959
Max Act: 6.7272. Min Act: -0.1700
Data Index: 8358911 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19