Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4146 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.5695. Min Act: -0.1700
Data Index: 5819520 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.5695. Min Act: -0.1700
Data Index: 4720892 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.5695. Min Act: -0.1700
Data Index: 3397253 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.5534. Min Act: -0.1700
Data Index: 6051071 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.5534. Min Act: -0.1700
Data Index: 1805831 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.5534. Min Act: -0.1700
Data Index: 5859139 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.5372. Min Act: -0.1700
Data Index: 2048286 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.5210. Min Act: -0.1700
Data Index: 6477341 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.5049. Min Act: -0.1700
Data Index: 1332571 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.5049. Min Act: -0.1700
Data Index: 3019995 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.4887. Min Act: -0.1700
Data Index: 4162586 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.5049. Min Act: -0.1700
Data Index: 4306112 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.4887. Min Act: -0.1700
Data Index: 8823110 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.4887. Min Act: -0.1700
Data Index: 1084434 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.4887. Min Act: -0.1700
Data Index: 7303425 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.4887. Min Act: -0.1700
Data Index: 3750111 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.4562. Min Act: -0.1700
Data Index: 6074775 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.4724. Min Act: -0.1700
Data Index: 6182007 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.4724. Min Act: -0.1700
Data Index: 6341542 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5695. Min Range: -2.5695
Max Act: 2.4562. Min Act: -0.1700
Data Index: 1159947 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19