Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2280 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.4780. Min Act: -0.1699
Data Index: 2648083 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.4468. Min Act: -0.1700
Data Index: 2220248 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.4468. Min Act: -0.1700
Data Index: 6056339 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.4155. Min Act: -0.1700
Data Index: 115061 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.3843. Min Act: -0.1700
Data Index: 8565738 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.2905. Min Act: -0.1700
Data Index: 63162 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.3218. Min Act: -0.1700
Data Index: 4709099 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1968. Min Act: -0.1700
Data Index: 8670197 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.2280. Min Act: -0.1700
Data Index: 2417226 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.2280. Min Act: -0.1700
Data Index: 1977158 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.2280. Min Act: -0.1700
Data Index: 2726282 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.2280. Min Act: -0.1700
Data Index: 413086 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1968. Min Act: -0.1700
Data Index: 8822983 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1968. Min Act: -0.1700
Data Index: 8495281 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1655. Min Act: -0.1700
Data Index: 7438579 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1655. Min Act: -0.1700
Data Index: 8302568 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1655. Min Act: -0.1700
Data Index: 2077076 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1343. Min Act: -0.1700
Data Index: 4190191 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.0718. Min Act: -0.1700
Data Index: 5377941 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4780. Min Range: -5.4780
Max Act: 5.1030. Min Act: -0.1700
Data Index: 8098879 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19