Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1812 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.5846. Min Act: -0.1700
Data Index: 6817754 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.5846. Min Act: -0.1700
Data Index: 406290 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.5533. Min Act: -0.1700
Data Index: 5040868 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.5533. Min Act: -0.1700
Data Index: 7296268 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.5533. Min Act: -0.1700
Data Index: 105523 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.4283. Min Act: -0.1700
Data Index: 25914 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.3346. Min Act: -0.1700
Data Index: 6319225 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.3346. Min Act: -0.1700
Data Index: 1694463 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.3033. Min Act: -0.1700
Data Index: 1947432 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.3033. Min Act: -0.1700
Data Index: 4099836 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.2096. Min Act: -0.1700
Data Index: 1163415 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.2408. Min Act: -0.1700
Data Index: 2153108 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.2096. Min Act: -0.1700
Data Index: 3823172 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.1783. Min Act: -0.1700
Data Index: 1610851 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.2096. Min Act: -0.1700
Data Index: 8686697 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.1783. Min Act: -0.1700
Data Index: 1584307 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.1783. Min Act: -0.1700
Data Index: 7971127 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.1783. Min Act: -0.1700
Data Index: 1823595 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.1471. Min Act: -0.1700
Data Index: 7295984 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5846. Min Range: -6.5846
Max Act: 6.1471. Min Act: -0.1700
Data Index: 1619200 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19