Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3196 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.6633. Min Act: -0.1700
Data Index: 3171410 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.4446. Min Act: -0.1700
Data Index: 4548002 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.2571. Min Act: -0.1700
Data Index: 2722842 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.2571. Min Act: -0.1700
Data Index: 1051817 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.1633. Min Act: -0.1700
Data Index: 1907287 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.1008. Min Act: -0.1700
Data Index: 4523031 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.1008. Min Act: -0.1700
Data Index: 8084063 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.1008. Min Act: -0.1700
Data Index: 5011564 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.0696. Min Act: -0.1700
Data Index: 2730269 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.0071. Min Act: -0.1700
Data Index: 3992224 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.0383. Min Act: -0.1700
Data Index: 4647773 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.0383. Min Act: -0.1700
Data Index: 894855 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6633. Min Range: -7.6633
Max Act: 6.9758. Min Act: -0.1700
Data Index: 2391592 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6633. Min Range: -7.6633
Max Act: 7.0071. Min Act: -0.1700
Data Index: 6729117 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6633. Min Range: -7.6633
Max Act: 6.9758. Min Act: -0.1700
Data Index: 5011563 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6633. Min Range: -7.6633
Max Act: 6.9758. Min Act: -0.1700
Data Index: 989846 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6633. Min Range: -7.6633
Max Act: 6.9446. Min Act: -0.1700
Data Index: 5869152 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6633. Min Range: -7.6633
Max Act: 6.9446. Min Act: -0.1700
Data Index: 3225825 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6633. Min Range: -7.6633
Max Act: 6.9758. Min Act: -0.1700
Data Index: 4929293 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6633. Min Range: -7.6633
Max Act: 6.9133. Min Act: -0.1700
Data Index: 5578827 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #19