Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4048 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1340. Min Range: -4.1340
Max Act: 4.1340. Min Act: -0.1700
Data Index: 6970530 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.9465. Min Act: -0.1700
Data Index: 7395981 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.9152. Min Act: -0.1700
Data Index: 44280 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.8214. Min Act: -0.1700
Data Index: 2091371 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.7276. Min Act: -0.1700
Data Index: 2038808 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.7276. Min Act: -0.1700
Data Index: 2923036 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.7276. Min Act: -0.1700
Data Index: 7799522 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.7276. Min Act: -0.1700
Data Index: 3302588 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.6337. Min Act: -0.1700
Data Index: 7415008 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.6650. Min Act: -0.1700
Data Index: 4900765 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.6650. Min Act: -0.1700
Data Index: 3315394 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.6650. Min Act: -0.1700
Data Index: 6131293 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.6337. Min Act: -0.1700
Data Index: 8568533 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.6337. Min Act: -0.1700
Data Index: 4647258 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.6337. Min Act: -0.1700
Data Index: 7224568 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.6337. Min Act: -0.1700
Data Index: 2105182 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.6337. Min Act: -0.1700
Data Index: 7010452 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.6024. Min Act: -0.1700
Data Index: 5936981 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.6024. Min Act: -0.1700
Data Index: 1417995 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1340. Min Range: -4.1340
Max Act: 3.6024. Min Act: -0.1700
Data Index: 7323588 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19