Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4065 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.7086. Min Act: -0.1700
Data Index: 2203279 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.7399. Min Act: -0.1700
Data Index: 7926850 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.7711. Min Act: -0.1700
Data Index: 7864653 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.7086. Min Act: -0.1700
Data Index: 5617087 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.7086. Min Act: -0.1700
Data Index: 4061139 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.7086. Min Act: -0.1700
Data Index: 1397312 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6774. Min Act: -0.1700
Data Index: 1954142 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6461. Min Act: -0.1700
Data Index: 3549687 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6461. Min Act: -0.1700
Data Index: 7015501 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6461. Min Act: -0.1697
Data Index: 1490100 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6461. Min Act: -0.1700
Data Index: 429795 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6149. Min Act: -0.1700
Data Index: 5327555 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6149. Min Act: -0.1700
Data Index: 5975459 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6149. Min Act: -0.1700
Data Index: 7635805 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6149. Min Act: -0.1700
Data Index: 669331 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6149. Min Act: -0.1700
Data Index: 4380174 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6149. Min Act: -0.1700
Data Index: 7304637 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6149. Min Act: -0.1700
Data Index: 7282845 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.6149. Min Act: -0.1700
Data Index: 4034080 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7711. Min Range: -5.7711
Max Act: 5.5836. Min Act: -0.1700
Data Index: 766768 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19