Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3625 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.8781. Min Act: -0.1700
Data Index: 8199019 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.8463. Min Act: -0.1700
Data Index: 7385447 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.8304. Min Act: -0.1700
Data Index: 1565131 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.8145. Min Act: -0.1700
Data Index: 1092416 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7986. Min Act: -0.1700
Data Index: 425340 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.8145. Min Act: -0.1700
Data Index: 5537299 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7986. Min Act: -0.1700
Data Index: 8797720 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7986. Min Act: -0.1700
Data Index: 8036176 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7826. Min Act: -0.1700
Data Index: 8267366 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7826. Min Act: -0.1700
Data Index: 7385446 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7507. Min Act: -0.1700
Data Index: 6538882 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7507. Min Act: -0.1700
Data Index: 7041802 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7507. Min Act: -0.1700
Data Index: 5714716 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7348. Min Act: -0.1700
Data Index: 3816317 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7188. Min Act: -0.1700
Data Index: 6172528 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7188. Min Act: -0.1700
Data Index: 2204077 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7188. Min Act: -0.1700
Data Index: 2225691 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7348. Min Act: -0.1700
Data Index: 6413114 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7348. Min Act: -0.1700
Data Index: 4556745 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8781. Min Range: -2.8781
Max Act: 2.7188. Min Act: -0.1700
Data Index: 8261887 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19