Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4133 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.9093. Min Act: -0.1700
Data Index: 6301168 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.8468. Min Act: -0.1700
Data Index: 3821865 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.7843. Min Act: -0.1700
Data Index: 3983812 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.7218. Min Act: -0.1700
Data Index: 148445 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.5343. Min Act: -0.1700
Data Index: 3164442 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.5343. Min Act: -0.1700
Data Index: 7907014 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.4718. Min Act: -0.1700
Data Index: 105976 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.4718. Min Act: -0.1700
Data Index: 6889802 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.4093. Min Act: -0.1700
Data Index: 8544061 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.4093. Min Act: -0.1700
Data Index: 7614107 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.4718. Min Act: -0.1700
Data Index: 174776 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.3468. Min Act: -0.1700
Data Index: 6118539 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.3468. Min Act: -0.1700
Data Index: 7045737 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.2843. Min Act: -0.1700
Data Index: 2231068 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.2843. Min Act: -0.1700
Data Index: 1754378 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.2843. Min Act: -0.1700
Data Index: 4156813 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.2843. Min Act: -0.1700
Data Index: 2590199 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.2843. Min Act: -0.1700
Data Index: 6919930 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.2843. Min Act: -0.1700
Data Index: 230830 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9093. Min Range: -8.9093
Max Act: 8.2218. Min Act: -0.1700
Data Index: 2141062 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19