Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.8168. Min Act: -0.1700
Data Index: 5378412 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.7855. Min Act: -0.1700
Data Index: 5372695 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.7229. Min Act: -0.1700
Data Index: 8246086 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.7542. Min Act: -0.1700
Data Index: 2816738 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.7229. Min Act: -0.1700
Data Index: 3829400 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.7542. Min Act: -0.1700
Data Index: 4445112 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.7229. Min Act: -0.1700
Data Index: 8215089 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.7073. Min Act: -0.1700
Data Index: 5443765 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.7073. Min Act: -0.1700
Data Index: 5378410 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.7073. Min Act: -0.1700
Data Index: 2413523 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.7073. Min Act: -0.1700
Data Index: 8519229 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.7073. Min Act: -0.1700
Data Index: 5188883 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.6916. Min Act: -0.1700
Data Index: 451552 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.6916. Min Act: -0.1700
Data Index: 8582496 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.6916. Min Act: -0.1700
Data Index: 1530729 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.6916. Min Act: -0.1700
Data Index: 6713749 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.6916. Min Act: -0.1700
Data Index: 2301926 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.6916. Min Act: -0.1700
Data Index: 1172538 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.6604. Min Act: -0.1700
Data Index: 343365 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8168. Min Range: -3.8168
Max Act: 3.6760. Min Act: -0.1700
Data Index: 1809900 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19