Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 500 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.8100. Min Act: -0.1700
Data Index: 1430797 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.7782. Min Act: -0.1700
Data Index: 5385689 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.7622. Min Act: -0.1700
Data Index: 2594887 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.7303. Min Act: -0.1700
Data Index: 2939785 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.7303. Min Act: -0.1700
Data Index: 4856751 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.7143. Min Act: -0.1700
Data Index: 1944945 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.7303. Min Act: -0.1700
Data Index: 3787514 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.7303. Min Act: -0.1700
Data Index: 7268836 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.7143. Min Act: -0.1700
Data Index: 5029597 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.6983. Min Act: -0.1700
Data Index: 3797224 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.7303. Min Act: -0.1700
Data Index: 1446335 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.7143. Min Act: -0.1700
Data Index: 4907815 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.6983. Min Act: -0.1700
Data Index: 7831513 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.6983. Min Act: -0.1700
Data Index: 8422770 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.6823. Min Act: -0.1700
Data Index: 4844816 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.6823. Min Act: -0.1700
Data Index: 7698056 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.7143. Min Act: -0.1700
Data Index: 2812510 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.6823. Min Act: -0.1700
Data Index: 7743948 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.6983. Min Act: -0.1700
Data Index: 3629207 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8100. Min Range: -2.8100
Max Act: 2.6502. Min Act: -0.1700
Data Index: 5522414 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19