Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5815 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.6983. Min Act: -0.1700
Data Index: 7729183 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.6358. Min Act: -0.1700
Data Index: 121868 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.6046. Min Act: -0.1700
Data Index: 5485047 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.6046. Min Act: -0.1700
Data Index: 6545198 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.6358. Min Act: -0.1700
Data Index: 4972055 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5733. Min Act: -0.1700
Data Index: 4539953 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5733. Min Act: -0.1700
Data Index: 2001549 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5733. Min Act: -0.1700
Data Index: 1343651 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5421. Min Act: -0.1700
Data Index: 6460471 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5421. Min Act: -0.1700
Data Index: 8623858 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5421. Min Act: -0.1700
Data Index: 8736293 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5421. Min Act: -0.1700
Data Index: 6634740 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5421. Min Act: -0.1700
Data Index: 4731492 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5421. Min Act: -0.1700
Data Index: 7246907 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5108. Min Act: -0.1700
Data Index: 7421603 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5421. Min Act: -0.1700
Data Index: 1161481 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5108. Min Act: -0.1700
Data Index: 6291692 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.4796. Min Act: -0.1700
Data Index: 6148630 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5108. Min Act: -0.1700
Data Index: 6095263 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5108. Min Act: -0.1700
Data Index: 3563923 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19