Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 269 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3824. Min Range: -7.3824
Max Act: 7.3824. Min Act: -0.1700
Data Index: 2414361 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3824. Min Range: -7.3824
Max Act: 7.2262. Min Act: -0.1700
Data Index: 6143371 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3824. Min Range: -7.3824
Max Act: 7.2574. Min Act: -0.1700
Data Index: 2531846 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3824. Min Range: -7.3824
Max Act: 7.1324. Min Act: -0.1700
Data Index: 4768519 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3824. Min Range: -7.3824
Max Act: 7.0699. Min Act: -0.1700
Data Index: 3356393 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3824. Min Range: -7.3824
Max Act: 7.0699. Min Act: -0.1700
Data Index: 1882903 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3824. Min Range: -7.3824
Max Act: 7.0699. Min Act: -0.1700
Data Index: 4526589 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3824. Min Range: -7.3824
Max Act: 6.9762. Min Act: -0.1700
Data Index: 7852940 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3824. Min Range: -7.3824
Max Act: 7.0074. Min Act: -0.1700
Data Index: 7893302 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3824. Min Range: -7.3824
Max Act: 7.0074. Min Act: -0.1700
Data Index: 804205 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3824. Min Range: -7.3824
Max Act: 6.9762. Min Act: -0.1700
Data Index: 8010545 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3824. Min Range: -7.3824
Max Act: 6.9449. Min Act: -0.1700
Data Index: 4031552 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3824. Min Range: -7.3824
Max Act: 6.9449. Min Act: -0.1700
Data Index: 8165121 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3824. Min Range: -7.3824
Max Act: 6.9137. Min Act: -0.1700
Data Index: 1670277 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3824. Min Range: -7.3824
Max Act: 6.9449. Min Act: -0.1700
Data Index: 884494 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3824. Min Range: -7.3824
Max Act: 6.9137. Min Act: -0.1700
Data Index: 6020040 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3824. Min Range: -7.3824
Max Act: 6.9137. Min Act: -0.1700
Data Index: 5026538 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3824. Min Range: -7.3824
Max Act: 6.9449. Min Act: -0.1700
Data Index: 8323237 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3824. Min Range: -7.3824
Max Act: 6.9137. Min Act: -0.1700
Data Index: 235423 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3824. Min Range: -7.3824
Max Act: 6.8824. Min Act: -0.1700
Data Index: 2811711 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19