Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4070 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.6330. Min Act: -0.1700
Data Index: 3555350 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4455. Min Range: -7.4455
Max Act: 7.2892. Min Act: -0.1700
Data Index: 4553031 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.8830. Min Act: -0.1700
Data Index: 6413453 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4455. Min Range: -7.4455
Max Act: 4.5080. Min Act: -0.1700
Data Index: 8632873 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.6955. Min Act: -0.1700
Data Index: 6778691 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.5705. Min Act: -0.1700
Data Index: 8584628 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.4767. Min Act: -0.1700
Data Index: 8734494 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4455. Min Range: -7.4455
Max Act: 7.0080. Min Act: -0.1700
Data Index: 6248592 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4455. Min Range: -7.4455
Max Act: 4.6330. Min Act: -0.1700
Data Index: 2363039 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.3205. Min Act: -0.1700
Data Index: 1985922 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.3517. Min Act: -0.1700
Data Index: 7691898 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.5392. Min Act: -0.1700
Data Index: 6496265 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.5080. Min Act: -0.1700
Data Index: 2143090 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4455. Min Range: -7.4455
Max Act: 4.4455. Min Act: -0.1700
Data Index: 7721230 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.1955. Min Act: -0.1700
Data Index: 2917772 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4455. Min Range: -7.4455
Max Act: 7.4455. Min Act: -0.1700
Data Index: 8668571 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.1017. Min Act: -0.1700
Data Index: 373869 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4455. Min Range: -7.4455
Max Act: 5.0080. Min Act: -0.1700
Data Index: 4166974 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.0080. Min Act: -0.1700
Data Index: 6828237 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4455. Min Range: -7.4455
Max Act: 6.0705. Min Act: -0.1700
Data Index: 123820 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19