Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1810 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.3994. Min Act: -0.1700
Data Index: 2700240 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.3369. Min Act: -0.1700
Data Index: 5377249 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.3057. Min Act: -0.1700
Data Index: 504113 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.2119. Min Act: -0.1700
Data Index: 346572 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.2119. Min Act: -0.1700
Data Index: 4003545 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.1807. Min Act: -0.1700
Data Index: 8407551 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.1807. Min Act: -0.1700
Data Index: 6118564 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.1494. Min Act: -0.1700
Data Index: 2454325 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.1807. Min Act: -0.1700
Data Index: 5466874 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.1494. Min Act: -0.1700
Data Index: 5869448 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.1182. Min Act: -0.1700
Data Index: 1374107 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.1807. Min Act: -0.1700
Data Index: 4501466 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.1182. Min Act: -0.1700
Data Index: 277772 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.1494. Min Act: -0.1700
Data Index: 4883874 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.0869. Min Act: -0.1700
Data Index: 2537487 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.1182. Min Act: -0.1700
Data Index: 5246231 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.0869. Min Act: -0.1700
Data Index: 1872116 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.0557. Min Act: -0.1700
Data Index: 5037110 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.0869. Min Act: -0.1700
Data Index: 6832472 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3994. Min Range: -6.3994
Max Act: 6.0869. Min Act: -0.1700
Data Index: 4566156 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19