Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3911 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.2609. Min Act: -0.1700
Data Index: 3303952 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.2278. Min Act: -0.1700
Data Index: 1071792 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.2112. Min Act: -0.1700
Data Index: 8119329 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1946. Min Act: -0.1700
Data Index: 6693130 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.2112. Min Act: -0.1700
Data Index: 123776 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1946. Min Act: -0.1700
Data Index: 3786027 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1946. Min Act: -0.1700
Data Index: 6105538 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1780. Min Act: -0.1700
Data Index: 1841076 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1780. Min Act: -0.1700
Data Index: 1023175 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1780. Min Act: -0.1700
Data Index: 4652306 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1447. Min Act: -0.1700
Data Index: 2347415 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1447. Min Act: -0.1700
Data Index: 3196501 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1614. Min Act: -0.1700
Data Index: 188591 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1447. Min Act: -0.1700
Data Index: 3028027 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1447. Min Act: -0.1700
Data Index: 5225370 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1280. Min Act: -0.1700
Data Index: 6422433 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1280. Min Act: -0.1700
Data Index: 780559 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1447. Min Act: -0.1700
Data Index: 11525 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1113. Min Act: -0.1700
Data Index: 4127239 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2609. Min Range: -2.2609
Max Act: 2.1280. Min Act: -0.1700
Data Index: 3622141 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #19