Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3802 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1140. Min Range: -4.1140
Max Act: 4.1140. Min Act: -0.1700
Data Index: 446465 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.7857. Min Act: -0.1700
Data Index: 4009552 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.7701. Min Act: -0.1700
Data Index: 6421757 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.7388. Min Act: -0.1700
Data Index: 7426118 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.7075. Min Act: -0.1700
Data Index: 7426122 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.6762. Min Act: -0.1700
Data Index: 3669661 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.6762. Min Act: -0.1700
Data Index: 5225049 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.6762. Min Act: -0.1700
Data Index: 5001860 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.6293. Min Act: -0.1700
Data Index: 2897298 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.6293. Min Act: -0.1700
Data Index: 6561403 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.6136. Min Act: -0.1700
Data Index: 7198478 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.6293. Min Act: -0.1700
Data Index: 8474258 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5980. Min Act: -0.1700
Data Index: 3428021 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5823. Min Act: -0.1700
Data Index: 5649805 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5823. Min Act: -0.1700
Data Index: 6171609 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5510. Min Act: -0.1700
Data Index: 7976980 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5197. Min Act: -0.1700
Data Index: 3672490 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5353. Min Act: -0.1700
Data Index: 2599621 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5197. Min Act: -0.1700
Data Index: 1980121 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1140. Min Range: -4.1140
Max Act: 3.5197. Min Act: -0.1700
Data Index: 219936 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19