Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 683 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.7552. Min Act: -0.1700
Data Index: 256091 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.6927. Min Act: -0.1700
Data Index: 6332781 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.5989. Min Act: -0.1700
Data Index: 7130392 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.5364. Min Act: -0.1700
Data Index: 6259200 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.5677. Min Act: -0.1700
Data Index: 452195 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.5364. Min Act: -0.1700
Data Index: 8107567 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.5052. Min Act: -0.1700
Data Index: 6332631 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.5052. Min Act: -0.1700
Data Index: 3513362 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.4739. Min Act: -0.1700
Data Index: 7730144 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.4739. Min Act: -0.1700
Data Index: 6108778 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.4739. Min Act: -0.1700
Data Index: 4530246 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.4427. Min Act: -0.1700
Data Index: 781915 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.4739. Min Act: -0.1700
Data Index: 6152916 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.4427. Min Act: -0.1700
Data Index: 2003692 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.4427. Min Act: -0.1700
Data Index: 7096081 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.4114. Min Act: -0.1700
Data Index: 8645051 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.3802. Min Act: -0.1700
Data Index: 3029663 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.3802. Min Act: -0.1700
Data Index: 6800564 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.3489. Min Act: -0.1700
Data Index: 195436 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7552. Min Range: -7.7552
Max Act: 7.3802. Min Act: -0.1700
Data Index: 5388856 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19