Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3278 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.1651. Min Range: -10.1651
Max Act: 10.1651. Min Act: -0.1700
Data Index: 3948202 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.9776. Min Act: -0.1700
Data Index: 1557394 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.9776. Min Act: -0.1700
Data Index: 4180058 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.7276. Min Act: -0.1700
Data Index: 2689894 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.7901. Min Act: -0.1700
Data Index: 7697228 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.7276. Min Act: -0.1700
Data Index: 1293436 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.6026. Min Act: -0.1700
Data Index: 4056862 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.6026. Min Act: -0.1700
Data Index: 3168777 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.4776. Min Act: -0.1700
Data Index: 6580567 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.5401. Min Act: -0.1700
Data Index: 6303584 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.5401. Min Act: -0.1700
Data Index: 8391447 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.5401. Min Act: -0.1700
Data Index: 5608410 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.4776. Min Act: -0.1700
Data Index: 8073862 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.4776. Min Act: -0.1700
Data Index: 7302433 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.4776. Min Act: -0.1700
Data Index: 5986841 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.4151. Min Act: -0.1700
Data Index: 2833669 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.4776. Min Act: -0.1700
Data Index: 75518 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.4151. Min Act: -0.1700
Data Index: 724437 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.4776. Min Act: -0.1700
Data Index: 6310284 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1651. Min Range: -10.1651
Max Act: 9.4776. Min Act: -0.1700
Data Index: 2868047 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19