Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1018 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.4442. Min Act: -0.1700
Data Index: 5465001 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.3344. Min Act: -0.1700
Data Index: 2872050 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.2716. Min Act: -0.1700
Data Index: 316647 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.2402. Min Act: -0.1700
Data Index: 5095507 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.2402. Min Act: -0.1700
Data Index: 6417318 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.2088. Min Act: -0.1700
Data Index: 1757901 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.2245. Min Act: -0.1700
Data Index: 3748360 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.1930. Min Act: -0.1700
Data Index: 7470828 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.2402. Min Act: -0.1700
Data Index: 7957154 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.1930. Min Act: -0.1700
Data Index: 5182180 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.1616. Min Act: -0.1700
Data Index: 4748943 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.2088. Min Act: -0.1700
Data Index: 2049385 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.1458. Min Act: -0.1700
Data Index: 1947020 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.0986. Min Act: -0.1700
Data Index: 8636759 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.0512. Min Act: -0.1700
Data Index: 5276052 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.0512. Min Act: -0.1700
Data Index: 8479121 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.0670. Min Act: -0.1700
Data Index: 179125 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.0355. Min Act: -0.1700
Data Index: 8650305 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.0197. Min Act: -0.1700
Data Index: 8441608 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4442. Min Range: -3.4442
Max Act: 3.0039. Min Act: -0.1700
Data Index: 97620 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #19