Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2266 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4613. Min Range: -7.4613
Max Act: 7.4613. Min Act: -0.1700
Data Index: 3143168 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4613. Min Range: -7.4613
Max Act: 7.3363. Min Act: -0.1700
Data Index: 5946044 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4613. Min Range: -7.4613
Max Act: 7.3050. Min Act: -0.1700
Data Index: 3460429 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4613. Min Range: -7.4613
Max Act: 7.2113. Min Act: -0.1700
Data Index: 907220 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4613. Min Range: -7.4613
Max Act: 7.1800. Min Act: -0.1700
Data Index: 6944634 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4613. Min Range: -7.4613
Max Act: 7.1488. Min Act: -0.1700
Data Index: 7830480 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4613. Min Range: -7.4613
Max Act: 7.1175. Min Act: -0.1700
Data Index: 7589501 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4613. Min Range: -7.4613
Max Act: 7.0238. Min Act: -0.1700
Data Index: 5693750 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4613. Min Range: -7.4613
Max Act: 7.0238. Min Act: -0.1700
Data Index: 1581166 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4613. Min Range: -7.4613
Max Act: 7.0550. Min Act: -0.1700
Data Index: 1625496 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4613. Min Range: -7.4613
Max Act: 7.0238. Min Act: -0.1700
Data Index: 7957240 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4613. Min Range: -7.4613
Max Act: 6.9925. Min Act: -0.1700
Data Index: 3723154 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4613. Min Range: -7.4613
Max Act: 6.9925. Min Act: -0.1700
Data Index: 4656082 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4613. Min Range: -7.4613
Max Act: 6.9925. Min Act: -0.1700
Data Index: 7808073 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4613. Min Range: -7.4613
Max Act: 6.9925. Min Act: -0.1700
Data Index: 3039041 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4613. Min Range: -7.4613
Max Act: 6.9613. Min Act: -0.1700
Data Index: 7086718 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4613. Min Range: -7.4613
Max Act: 6.9925. Min Act: -0.1700
Data Index: 8331876 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4613. Min Range: -7.4613
Max Act: 6.9300. Min Act: -0.1700
Data Index: 3455082 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4613. Min Range: -7.4613
Max Act: 6.9300. Min Act: -0.1700
Data Index: 6959271 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4613. Min Range: -7.4613
Max Act: 6.8675. Min Act: -0.1700
Data Index: 1118396 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #19