Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 655 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.5976. Min Range: -7.5976
Max Act: 7.5976. Min Act: -0.1700
Data Index: 1088324 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5976. Min Range: -7.5976
Max Act: 7.4101. Min Act: -0.1700
Data Index: 2608078 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5976. Min Range: -7.5976
Max Act: 7.2851. Min Act: -0.1700
Data Index: 1443480 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5976. Min Range: -7.5976
Max Act: 7.3476. Min Act: -0.1700
Data Index: 501546 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5976. Min Range: -7.5976
Max Act: 7.2226. Min Act: -0.1700
Data Index: 6142379 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5976. Min Range: -7.5976
Max Act: 7.1601. Min Act: -0.1700
Data Index: 1946448 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5976. Min Range: -7.5976
Max Act: 7.0976. Min Act: -0.1700
Data Index: 4816465 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5976. Min Range: -7.5976
Max Act: 7.0976. Min Act: -0.1700
Data Index: 7449326 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5976. Min Range: -7.5976
Max Act: 7.0039. Min Act: -0.1700
Data Index: 7489865 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5976. Min Range: -7.5976
Max Act: 6.9414. Min Act: -0.1700
Data Index: 4340570 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5976. Min Range: -7.5976
Max Act: 6.9726. Min Act: -0.1700
Data Index: 6216022 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5976. Min Range: -7.5976
Max Act: 6.9726. Min Act: -0.1700
Data Index: 1113479 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5976. Min Range: -7.5976
Max Act: 6.9101. Min Act: -0.1700
Data Index: 4830058 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5976. Min Range: -7.5976
Max Act: 6.9101. Min Act: -0.1700
Data Index: 1242541 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5976. Min Range: -7.5976
Max Act: 6.9726. Min Act: -0.1700
Data Index: 1011248 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5976. Min Range: -7.5976
Max Act: 6.9414. Min Act: -0.1700
Data Index: 4877390 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5976. Min Range: -7.5976
Max Act: 6.9726. Min Act: -0.1700
Data Index: 7696914 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5976. Min Range: -7.5976
Max Act: 6.9101. Min Act: -0.1700
Data Index: 5856784 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5976. Min Range: -7.5976
Max Act: 6.9101. Min Act: -0.1700
Data Index: 7345966 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5976. Min Range: -7.5976
Max Act: 6.9101. Min Act: -0.1700
Data Index: 1178862 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19