Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2056 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3954. Min Range: -7.3954
Max Act: 7.3954. Min Act: -0.1700
Data Index: 3222993 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3954. Min Range: -7.3954
Max Act: 7.1141. Min Act: -0.1700
Data Index: 4465956 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.9579. Min Act: -0.1700
Data Index: 6816436 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.9579. Min Act: -0.1700
Data Index: 1969531 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.9579. Min Act: -0.1700
Data Index: 346700 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.8954. Min Act: -0.1700
Data Index: 4933274 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.8954. Min Act: -0.1700
Data Index: 7784597 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.8954. Min Act: -0.1700
Data Index: 4274263 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.8329. Min Act: -0.1700
Data Index: 5458292 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.8329. Min Act: -0.1700
Data Index: 2293275 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.8016. Min Act: -0.1700
Data Index: 1469621 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.7704. Min Act: -0.1700
Data Index: 1956670 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.7704. Min Act: -0.1700
Data Index: 1240877 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.7079. Min Act: -0.1700
Data Index: 6539942 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.7079. Min Act: -0.1700
Data Index: 5748079 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.7079. Min Act: -0.1700
Data Index: 6357949 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.6766. Min Act: -0.1700
Data Index: 5499675 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.6454. Min Act: -0.1700
Data Index: 1672870 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.6454. Min Act: -0.1700
Data Index: 1539009 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3954. Min Range: -7.3954
Max Act: 6.6454. Min Act: -0.1700
Data Index: 6027103 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19