Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 590 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.5857. Min Act: -0.1700
Data Index: 5079556 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4920. Min Act: -0.1700
Data Index: 6185258 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.4920. Min Act: -0.1700
Data Index: 7840858 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3982. Min Act: -0.1700
Data Index: 1825556 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3670. Min Act: -0.1700
Data Index: 109717 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3982. Min Act: -0.1700
Data Index: 6389136 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3982. Min Act: -0.1700
Data Index: 242848 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3670. Min Act: -0.1700
Data Index: 3631097 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3357. Min Act: -0.1700
Data Index: 4420994 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3670. Min Act: -0.1700
Data Index: 2609221 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3357. Min Act: -0.1700
Data Index: 1207920 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3045. Min Act: -0.1700
Data Index: 2670990 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3045. Min Act: -0.1700
Data Index: 7940652 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.2732. Min Act: -0.1700
Data Index: 7055331 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3045. Min Act: -0.1700
Data Index: 5528130 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.3045. Min Act: -0.1700
Data Index: 1733126 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.2732. Min Act: -0.1700
Data Index: 1169531 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.2732. Min Act: -0.1700
Data Index: 4363707 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.2420. Min Act: -0.1700
Data Index: 6763175 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5857. Min Range: -4.5857
Max Act: 4.2732. Min Act: -0.1700
Data Index: 5375423 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19