Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 846 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.3134. Min Act: -0.1700
Data Index: 4887315 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.2663. Min Act: -0.1700
Data Index: 558204 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.2663. Min Act: -0.1700
Data Index: 1914947 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.2349. Min Act: -0.1700
Data Index: 102177 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.2035. Min Act: -0.1700
Data Index: 6184094 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.2035. Min Act: -0.1700
Data Index: 2750091 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1405. Min Act: -0.1700
Data Index: 578615 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1563. Min Act: -0.1700
Data Index: 554537 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1563. Min Act: -0.1700
Data Index: 6950052 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1248. Min Act: -0.1700
Data Index: 57641 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1563. Min Act: -0.1700
Data Index: 2723376 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1405. Min Act: -0.1700
Data Index: 1514338 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1248. Min Act: -0.1700
Data Index: 3688273 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1405. Min Act: -0.1700
Data Index: 4705266 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1248. Min Act: -0.1700
Data Index: 1192433 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1405. Min Act: -0.1700
Data Index: 7272320 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1405. Min Act: -0.1700
Data Index: 892477 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1248. Min Act: -0.1700
Data Index: 7586004 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.1090. Min Act: -0.1700
Data Index: 4194672 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3134. Min Range: -3.3134
Max Act: 3.0775. Min Act: -0.1700
Data Index: 452806 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #19