Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4538 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.6036. Min Act: -0.1700
Data Index: 7248484 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.6036. Min Act: -0.1700
Data Index: 651358 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.6036. Min Act: -0.1700
Data Index: 310964 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.5411. Min Act: -0.1700
Data Index: 6055424 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.3536. Min Act: -0.1700
Data Index: 4637434 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.3848. Min Act: -0.1700
Data Index: 2768580 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.3536. Min Act: -0.1700
Data Index: 5941188 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.3223. Min Act: -0.1700
Data Index: 2329944 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.2911. Min Act: -0.1700
Data Index: 7175174 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.2911. Min Act: -0.1700
Data Index: 3027059 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.2911. Min Act: -0.1700
Data Index: 2104240 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.2911. Min Act: -0.1700
Data Index: 6076227 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.2911. Min Act: -0.1700
Data Index: 1189521 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.2598. Min Act: -0.1700
Data Index: 4380732 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.1661. Min Act: -0.1700
Data Index: 1501231 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.1661. Min Act: -0.1700
Data Index: 6444692 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.1661. Min Act: -0.1700
Data Index: 1897483 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.1348. Min Act: -0.1700
Data Index: 3349524 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.1661. Min Act: -0.1700
Data Index: 7854606 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6036. Min Range: -7.6036
Max Act: 7.1348. Min Act: -0.1700
Data Index: 7572890 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19