Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1683 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.4155. Min Act: -0.1700
Data Index: 5528724 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.3843. Min Act: -0.1700
Data Index: 5829703 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.3843. Min Act: -0.1700
Data Index: 113272 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.3843. Min Act: -0.1700
Data Index: 4225821 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.3530. Min Act: -0.1700
Data Index: 1360949 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.3218. Min Act: -0.1700
Data Index: 7077143 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.2593. Min Act: -0.1700
Data Index: 2633793 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.1968. Min Act: -0.1700
Data Index: 1384776 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.1655. Min Act: -0.1700
Data Index: 5994410 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.1968. Min Act: -0.1700
Data Index: 3317689 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.1343. Min Act: -0.1700
Data Index: 7393836 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.1343. Min Act: -0.1700
Data Index: 516236 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.1655. Min Act: -0.1700
Data Index: 1582693 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.1030. Min Act: -0.1700
Data Index: 5325493 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.1030. Min Act: -0.1700
Data Index: 6611782 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.0718. Min Act: -0.1700
Data Index: 2850965 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.0718. Min Act: -0.1700
Data Index: 526019 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.0405. Min Act: -0.1700
Data Index: 1458664 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4155. Min Range: -5.4155
Max Act: 4.9780. Min Act: -0.1700
Data Index: 1132120 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4155. Min Range: -5.4155
Max Act: 5.0405. Min Act: -0.1700
Data Index: 1819179 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #19