Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 58 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0433. Min Range: -9.0433
Max Act: 9.0433. Min Act: -0.1700
Data Index: 3176219 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.7933. Min Act: -0.1700
Data Index: 5518307 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.7308. Min Act: -0.1700
Data Index: 3107012 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.7308. Min Act: -0.1700
Data Index: 6019975 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.7308. Min Act: -0.1700
Data Index: 4471006 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.7308. Min Act: -0.1700
Data Index: 5894366 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.6683. Min Act: -0.1700
Data Index: 8325717 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.6683. Min Act: -0.1700
Data Index: 1624722 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.6683. Min Act: -0.1700
Data Index: 2496053 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.6683. Min Act: -0.1700
Data Index: 1914829 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.6058. Min Act: -0.1700
Data Index: 7528683 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.6058. Min Act: -0.1700
Data Index: 205993 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.5433. Min Act: -0.1700
Data Index: 8068938 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.5433. Min Act: -0.1700
Data Index: 1914823 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.4808. Min Act: -0.1700
Data Index: 3457044 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.4808. Min Act: -0.1700
Data Index: 5853407 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.4808. Min Act: -0.1700
Data Index: 8068924 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.4808. Min Act: -0.1700
Data Index: 2826540 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.4808. Min Act: -0.1700
Data Index: 2808713 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0433. Min Range: -9.0433
Max Act: 8.4808. Min Act: -0.1700
Data Index: 1169546 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #19