Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2987 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4264. Min Range: -8.4264
Max Act: 8.4264. Min Act: -0.1700
Data Index: 1798356 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4264. Min Range: -8.4264
Max Act: 8.1764. Min Act: -0.1700
Data Index: 1835540 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4264. Min Range: -8.4264
Max Act: 8.1139. Min Act: -0.1700
Data Index: 4578539 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4264. Min Range: -8.4264
Max Act: 8.0514. Min Act: -0.1700
Data Index: 1026594 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4264. Min Range: -8.4264
Max Act: 8.0514. Min Act: -0.1700
Data Index: 4500440 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.9889. Min Act: -0.1700
Data Index: 5311118 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4264. Min Range: -8.4264
Max Act: 8.0514. Min Act: -0.1700
Data Index: 7940753 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.9889. Min Act: -0.1700
Data Index: 5239801 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.9264. Min Act: -0.1700
Data Index: 6360938 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.9264. Min Act: -0.1700
Data Index: 424808 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.9264. Min Act: -0.1700
Data Index: 4210223 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.8639. Min Act: -0.1700
Data Index: 6187123 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.8639. Min Act: -0.1700
Data Index: 8295639 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.8639. Min Act: -0.1700
Data Index: 4596301 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.8639. Min Act: -0.1700
Data Index: 4258729 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.8014. Min Act: -0.1700
Data Index: 1823811 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.8014. Min Act: -0.1700
Data Index: 3824252 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.8014. Min Act: -0.1700
Data Index: 5161492 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.8014. Min Act: -0.1700
Data Index: 444469 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4264. Min Range: -8.4264
Max Act: 7.8014. Min Act: -0.1700
Data Index: 3291371 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19