Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 471 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.4642. Min Act: -0.1700
Data Index: 6786723 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.4017. Min Act: -0.1700
Data Index: 1749597 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.4017. Min Act: -0.1700
Data Index: 3762205 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.3392. Min Act: -0.1700
Data Index: 1934114 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.3705. Min Act: -0.1700
Data Index: 1673593 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.3392. Min Act: -0.1700
Data Index: 1905209 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.3392. Min Act: -0.1700
Data Index: 6822762 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2767. Min Act: -0.1700
Data Index: 2290406 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2767. Min Act: -0.1700
Data Index: 4577901 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2767. Min Act: -0.1700
Data Index: 3107501 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2767. Min Act: -0.1700
Data Index: 5421380 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2142. Min Act: -0.1700
Data Index: 1668930 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2455. Min Act: -0.1700
Data Index: 2244137 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2455. Min Act: -0.1700
Data Index: 3692919 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2455. Min Act: -0.1700
Data Index: 4829460 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2142. Min Act: -0.1700
Data Index: 3645237 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.1517. Min Act: -0.1700
Data Index: 6359740 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2142. Min Act: -0.1700
Data Index: 4356262 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.2142. Min Act: -0.1700
Data Index: 830674 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4642. Min Range: -4.4642
Max Act: 4.1830. Min Act: -0.1700
Data Index: 2536209 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19