Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6082 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.7061. Min Act: -0.1700
Data Index: 2273716 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.5811. Min Act: -0.1700
Data Index: 3151554 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.3936. Min Act: -0.1700
Data Index: 1103675 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.3311. Min Act: -0.1700
Data Index: 7961226 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.2061. Min Act: -0.1700
Data Index: 929792 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.1436. Min Act: -0.1700
Data Index: 2563296 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.1436. Min Act: -0.1700
Data Index: 3168648 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.1436. Min Act: -0.1700
Data Index: 1547419 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.0811. Min Act: -0.1700
Data Index: 4653886 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.0811. Min Act: -0.1700
Data Index: 5360040 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.0186. Min Act: -0.1700
Data Index: 6361344 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.0186. Min Act: -0.1700
Data Index: 3651484 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.0186. Min Act: -0.1700
Data Index: 1918945 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7061. Min Range: -8.7061
Max Act: 8.0186. Min Act: -0.1700
Data Index: 7473287 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7061. Min Range: -8.7061
Max Act: 7.8936. Min Act: -0.1700
Data Index: 6011299 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7061. Min Range: -8.7061
Max Act: 7.9561. Min Act: -0.1700
Data Index: 1772993 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7061. Min Range: -8.7061
Max Act: 7.8936. Min Act: -0.1700
Data Index: 3277059 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7061. Min Range: -8.7061
Max Act: 7.8936. Min Act: -0.1700
Data Index: 787685 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7061. Min Range: -8.7061
Max Act: 7.8311. Min Act: -0.1700
Data Index: 6521707 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7061. Min Range: -8.7061
Max Act: 7.8311. Min Act: -0.1700
Data Index: 6881287 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19