Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3447 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.3932. Min Act: -0.1700
Data Index: 4826726 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.3619. Min Act: -0.1700
Data Index: 6528489 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.2994. Min Act: -0.1700
Data Index: 6573089 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.2682. Min Act: -0.1700
Data Index: 4400088 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.2057. Min Act: -0.1700
Data Index: 6948130 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.2369. Min Act: -0.1700
Data Index: 4457997 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.2369. Min Act: -0.1700
Data Index: 8490911 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.2369. Min Act: -0.1700
Data Index: 7074746 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.2057. Min Act: -0.1700
Data Index: 8093708 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.2057. Min Act: -0.1700
Data Index: 6426011 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.1744. Min Act: -0.1700
Data Index: 3541844 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.1744. Min Act: -0.1700
Data Index: 934096 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.1744. Min Act: -0.1700
Data Index: 4590176 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.1119. Min Act: -0.1700
Data Index: 2827701 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.1432. Min Act: -0.1700
Data Index: 7001513 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.1744. Min Act: -0.1700
Data Index: 7760410 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.1432. Min Act: -0.1700
Data Index: 3737399 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.1119. Min Act: -0.1700
Data Index: 1709620 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.1432. Min Act: -0.1700
Data Index: 4188603 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3932. Min Range: -6.3932
Max Act: 6.1119. Min Act: -0.1700
Data Index: 24320 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19