Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2897 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4605. Min Range: -7.4605
Max Act: 7.4605. Min Act: -0.1700
Data Index: 344041 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4605. Min Range: -7.4605
Max Act: 7.2105. Min Act: -0.1700
Data Index: 5447356 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.9917. Min Act: -0.1700
Data Index: 7833388 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.9917. Min Act: -0.1700
Data Index: 51254 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.9605. Min Act: -0.1700
Data Index: 3988594 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.8980. Min Act: -0.1700
Data Index: 5199734 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.8355. Min Act: -0.1700
Data Index: 6614869 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.8980. Min Act: -0.1700
Data Index: 4485460 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.8355. Min Act: -0.1700
Data Index: 3904746 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.8355. Min Act: -0.1700
Data Index: 5310589 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.7730. Min Act: -0.1700
Data Index: 5575509 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.8042. Min Act: -0.1700
Data Index: 5129599 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.7730. Min Act: -0.1700
Data Index: 2221343 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.7730. Min Act: -0.1700
Data Index: 3346013 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.7730. Min Act: -0.1700
Data Index: 1444875 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.7105. Min Act: -0.1700
Data Index: 4226320 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.7105. Min Act: -0.1700
Data Index: 2074274 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.7417. Min Act: -0.1700
Data Index: 905630 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.7417. Min Act: -0.1700
Data Index: 6122585 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4605. Min Range: -7.4605
Max Act: 6.7105. Min Act: -0.1700
Data Index: 4042633 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #19