Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4128 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2182. Min Range: -6.2182
Max Act: 6.2182. Min Act: -0.1699
Data Index: 3369073 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2182. Min Range: -6.2182
Max Act: 6.0619. Min Act: -0.1700
Data Index: 3606635 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2182. Min Range: -6.2182
Max Act: 6.0619. Min Act: -0.1700
Data Index: 3427613 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9994. Min Act: -0.1700
Data Index: 5920492 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2182. Min Range: -6.2182
Max Act: 6.0307. Min Act: -0.1700
Data Index: 8261451 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9994. Min Act: -0.1700
Data Index: 2303851 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9994. Min Act: -0.1700
Data Index: 422866 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9682. Min Act: -0.1698
Data Index: 4333901 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9682. Min Act: -0.1700
Data Index: 8070114 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9682. Min Act: -0.1700
Data Index: 5013241 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9682. Min Act: -0.1700
Data Index: 2251145 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9057. Min Act: -0.1700
Data Index: 8392463 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9369. Min Act: -0.1700
Data Index: 1142956 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9682. Min Act: -0.1700
Data Index: 703205 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9369. Min Act: -0.1700
Data Index: 5631581 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9369. Min Act: -0.1700
Data Index: 422867 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9369. Min Act: -0.1700
Data Index: 7978513 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9369. Min Act: -0.1700
Data Index: 7887529 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9057. Min Act: -0.1700
Data Index: 6398405 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2182. Min Range: -6.2182
Max Act: 5.9057. Min Act: -0.1700
Data Index: 6659948 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19