Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3729 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1511. Min Range: -6.1511
Max Act: 6.1511. Min Act: -0.1700
Data Index: 3438093 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1511. Min Range: -6.1511
Max Act: 6.1199. Min Act: -0.1700
Data Index: 4191383 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1511. Min Range: -6.1511
Max Act: 6.0886. Min Act: -0.1700
Data Index: 5078520 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1511. Min Range: -6.1511
Max Act: 6.0886. Min Act: -0.1700
Data Index: 7356200 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1511. Min Range: -6.1511
Max Act: 6.0574. Min Act: -0.1700
Data Index: 8803467 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1511. Min Range: -6.1511
Max Act: 6.0261. Min Act: -0.1700
Data Index: 6064375 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1511. Min Range: -6.1511
Max Act: 6.0261. Min Act: -0.1700
Data Index: 5198043 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9949. Min Act: -0.1699
Data Index: 2927193 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9949. Min Act: -0.1700
Data Index: 3762869 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9949. Min Act: -0.1699
Data Index: 4998476 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9949. Min Act: -0.1700
Data Index: 7465826 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9949. Min Act: -0.1700
Data Index: 4006584 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9949. Min Act: -0.1700
Data Index: 1866792 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9949. Min Act: -0.1700
Data Index: 70576 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9636. Min Act: -0.1700
Data Index: 3773676 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9324. Min Act: -0.1700
Data Index: 3438098 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9011. Min Act: -0.1700
Data Index: 682920 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9324. Min Act: -0.1700
Data Index: 6083956 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9324. Min Act: -0.1700
Data Index: 3933914 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1511. Min Range: -6.1511
Max Act: 5.9324. Min Act: -0.1700
Data Index: 4549417 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #19