Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4824 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3133. Min Range: -5.3133
Max Act: 5.3133. Min Act: -0.1700
Data Index: 7030136 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3133. Min Range: -5.3133
Max Act: 5.2820. Min Act: -0.1700
Data Index: 7094118 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3133. Min Range: -5.3133
Max Act: 5.2195. Min Act: -0.1700
Data Index: 7484413 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3133. Min Range: -5.3133
Max Act: 5.1258. Min Act: -0.1700
Data Index: 3812639 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3133. Min Range: -5.3133
Max Act: 5.1258. Min Act: -0.1700
Data Index: 5299812 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3133. Min Range: -5.3133
Max Act: 5.0633. Min Act: -0.1700
Data Index: 3912106 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3133. Min Range: -5.3133
Max Act: 5.0945. Min Act: -0.1700
Data Index: 8168699 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3133. Min Range: -5.3133
Max Act: 5.0320. Min Act: -0.1700
Data Index: 3272527 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3133. Min Range: -5.3133
Max Act: 4.9695. Min Act: -0.1700
Data Index: 8552622 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3133. Min Range: -5.3133
Max Act: 4.9695. Min Act: -0.1700
Data Index: 2209492 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3133. Min Range: -5.3133
Max Act: 4.9383. Min Act: -0.1700
Data Index: 7628797 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3133. Min Range: -5.3133
Max Act: 4.9070. Min Act: -0.1700
Data Index: 8433177 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3133. Min Range: -5.3133
Max Act: 4.9070. Min Act: -0.1700
Data Index: 6854035 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3133. Min Range: -5.3133
Max Act: 4.9383. Min Act: -0.1700
Data Index: 3618983 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3133. Min Range: -5.3133
Max Act: 4.9070. Min Act: -0.1700
Data Index: 8390399 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3133. Min Range: -5.3133
Max Act: 4.9070. Min Act: -0.1700
Data Index: 3533338 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3133. Min Range: -5.3133
Max Act: 4.8758. Min Act: -0.1700
Data Index: 968828 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3133. Min Range: -5.3133
Max Act: 4.8758. Min Act: -0.1700
Data Index: 635160 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3133. Min Range: -5.3133
Max Act: 4.8758. Min Act: -0.1700
Data Index: 8346464 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3133. Min Range: -5.3133
Max Act: 4.8758. Min Act: -0.1700
Data Index: 7544162 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19