Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.4286. Min Act: -0.1700
Data Index: 2543875 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.3974. Min Act: -0.1700
Data Index: 8245368 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.3974. Min Act: -0.1700
Data Index: 1044561 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.3974. Min Act: -0.1700
Data Index: 8221348 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.3974. Min Act: -0.1700
Data Index: 6809243 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.3661. Min Act: -0.1700
Data Index: 5465 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.3349. Min Act: -0.1700
Data Index: 5611046 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.3349. Min Act: -0.1700
Data Index: 1169939 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.3349. Min Act: -0.1700
Data Index: 6028859 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.3661. Min Act: -0.1700
Data Index: 2683636 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.2724. Min Act: -0.1700
Data Index: 2097716 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.2724. Min Act: -0.1700
Data Index: 5856071 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.2411. Min Act: -0.1700
Data Index: 117506 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.2411. Min Act: -0.1700
Data Index: 4469826 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.2724. Min Act: -0.1700
Data Index: 7325533 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.2099. Min Act: -0.1700
Data Index: 3267950 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.2099. Min Act: -0.1700
Data Index: 2882883 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.2099. Min Act: -0.1700
Data Index: 3802236 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.1786. Min Act: -0.1700
Data Index: 4872111 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4286. Min Range: -5.4286
Max Act: 5.1786. Min Act: -0.1700
Data Index: 5004569 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19