Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1918 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.6980. Min Act: -0.1700
Data Index: 4376339 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.6668. Min Act: -0.1700
Data Index: 3202300 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.6980. Min Act: -0.1700
Data Index: 3306610 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.6668. Min Act: -0.1700
Data Index: 971647 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.6355. Min Act: -0.1700
Data Index: 1177253 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.6043. Min Act: -0.1700
Data Index: 2796377 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.6043. Min Act: -0.1700
Data Index: 666209 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.5418. Min Act: -0.1700
Data Index: 8006443 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.5730. Min Act: -0.1700
Data Index: 4978187 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.5418. Min Act: -0.1700
Data Index: 6712433 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.5418. Min Act: -0.1700
Data Index: 398619 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.5418. Min Act: -0.1700
Data Index: 805627 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.5105. Min Act: -0.1700
Data Index: 1146107 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.5105. Min Act: -0.1700
Data Index: 5127707 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.5105. Min Act: -0.1700
Data Index: 6175865 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.5105. Min Act: -0.1700
Data Index: 3887745 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.5105. Min Act: -0.1700
Data Index: 2404101 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.4793. Min Act: -0.1700
Data Index: 7942492 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.4793. Min Act: -0.1700
Data Index: 1235512 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6980. Min Range: -4.6980
Max Act: 4.4793. Min Act: -0.1700
Data Index: 81506 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19