Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1409 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.4905. Min Act: -0.1700
Data Index: 7294271 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.4280. Min Act: -0.1700
Data Index: 3314116 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.3968. Min Act: -0.1700
Data Index: 5511099 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.3343. Min Act: -0.1700
Data Index: 2892037 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.3343. Min Act: -0.1700
Data Index: 3568741 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.3343. Min Act: -0.1700
Data Index: 8626640 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.3343. Min Act: -0.1700
Data Index: 3314120 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.3030. Min Act: -0.1700
Data Index: 4031732 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.3030. Min Act: -0.1700
Data Index: 3915108 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.3030. Min Act: -0.1700
Data Index: 2867525 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.3030. Min Act: -0.1700
Data Index: 8319622 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.3030. Min Act: -0.1700
Data Index: 8253761 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.2718. Min Act: -0.1700
Data Index: 7785217 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.3030. Min Act: -0.1700
Data Index: 2340918 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.2718. Min Act: -0.1700
Data Index: 8444974 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.2718. Min Act: -0.1700
Data Index: 536576 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.2718. Min Act: -0.1700
Data Index: 7706694 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.2718. Min Act: -0.1700
Data Index: 1792795 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.2405. Min Act: -0.1700
Data Index: 3698969 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4905. Min Range: -4.4905
Max Act: 4.2405. Min Act: -0.1700
Data Index: 4798591 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #19