Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1147 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.9493. Min Act: -0.1700
Data Index: 2898499 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.7930. Min Act: -0.1700
Data Index: 4258347 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.7618. Min Act: -0.1700
Data Index: 1479587 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.7618. Min Act: -0.1700
Data Index: 7796006 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.7618. Min Act: -0.1700
Data Index: 5508151 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.7305. Min Act: -0.1700
Data Index: 1909703 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.6680. Min Act: -0.1700
Data Index: 2301203 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.6680. Min Act: -0.1700
Data Index: 1497009 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.6680. Min Act: -0.1700
Data Index: 881652 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.6368. Min Act: -0.1700
Data Index: 2563983 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.6680. Min Act: -0.1700
Data Index: 1909701 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.6993. Min Act: -0.1700
Data Index: 4464457 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.6368. Min Act: -0.1700
Data Index: 2885198 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.6680. Min Act: -0.1700
Data Index: 6825184 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.6055. Min Act: -0.1700
Data Index: 1071502 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.6055. Min Act: -0.1700
Data Index: 8018188 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.5743. Min Act: -0.1700
Data Index: 5508142 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.6055. Min Act: -0.1700
Data Index: 5972379 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.5743. Min Act: -0.1700
Data Index: 5306302 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9493. Min Range: -5.9493
Max Act: 5.5743. Min Act: -0.1700
Data Index: 5628188 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19