Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6397 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.6411. Min Act: -0.1700
Data Index: 3545002 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.6411. Min Act: -0.1700
Data Index: 8130376 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.4536. Min Act: -0.1700
Data Index: 2731831 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.5161. Min Act: -0.1700
Data Index: 3987895 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.4536. Min Act: -0.1700
Data Index: 6939436 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.3911. Min Act: -0.1700
Data Index: 1113207 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.3286. Min Act: -0.1700
Data Index: 1319063 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.3286. Min Act: -0.1700
Data Index: 4086241 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.3911. Min Act: -0.1700
Data Index: 6354901 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.3286. Min Act: -0.1700
Data Index: 5435514 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.3286. Min Act: -0.1700
Data Index: 5050953 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.3286. Min Act: -0.1700
Data Index: 1076130 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.2661. Min Act: -0.1700
Data Index: 6951531 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.2661. Min Act: -0.1700
Data Index: 6931605 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.2036. Min Act: -0.1700
Data Index: 8651328 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.1411. Min Act: -0.1700
Data Index: 430982 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.1411. Min Act: -0.1700
Data Index: 6450767 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.0786. Min Act: -0.1700
Data Index: 4702154 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.0786. Min Act: -0.1700
Data Index: 3578868 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6411. Min Range: -8.6411
Max Act: 8.0786. Min Act: -0.1700
Data Index: 6815960 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19