Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 666 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.5335. Min Act: -0.1700
Data Index: 5700619 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.3773. Min Act: -0.1700
Data Index: 4754923 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.3460. Min Act: -0.1700
Data Index: 7150787 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.2835. Min Act: -0.1700
Data Index: 5365893 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.2210. Min Act: -0.1700
Data Index: 6313106 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.2210. Min Act: -0.1700
Data Index: 8062389 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.1898. Min Act: -0.1700
Data Index: 1854914 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.1898. Min Act: -0.1700
Data Index: 4450558 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.1898. Min Act: -0.1700
Data Index: 2971165 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.1273. Min Act: -0.1700
Data Index: 1644252 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.0960. Min Act: -0.1700
Data Index: 962948 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.1273. Min Act: -0.1700
Data Index: 7709134 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.1273. Min Act: -0.1700
Data Index: 7450900 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.1273. Min Act: -0.1700
Data Index: 904835 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.1273. Min Act: -0.1700
Data Index: 3199651 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.0960. Min Act: -0.1700
Data Index: 6248494 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.0960. Min Act: -0.1700
Data Index: 8505666 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.0960. Min Act: -0.1700
Data Index: 1476366 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.0648. Min Act: -0.1700
Data Index: 3853111 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5335. Min Range: -4.5335
Max Act: 4.0335. Min Act: -0.1700
Data Index: 1489785 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #19