Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2788 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0892. Min Range: -7.0892
Max Act: 7.0892. Min Act: -0.1700
Data Index: 3925086 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0892. Min Range: -7.0892
Max Act: 7.0579. Min Act: -0.1700
Data Index: 1675183 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0892. Min Range: -7.0892
Max Act: 7.0892. Min Act: -0.1700
Data Index: 5868574 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0892. Min Range: -7.0892
Max Act: 7.0267. Min Act: -0.1697
Data Index: 897978 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.9329. Min Act: -0.1700
Data Index: 3632800 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.8392. Min Act: -0.1700
Data Index: 3032310 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.7767. Min Act: -0.1700
Data Index: 1680767 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.7142. Min Act: -0.1700
Data Index: 910489 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.6517. Min Act: -0.1700
Data Index: 7739231 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.5892. Min Act: -0.1700
Data Index: 3692048 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.4954. Min Act: -0.1699
Data Index: 43976 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.5267. Min Act: -0.1700
Data Index: 2706070 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.4954. Min Act: -0.1700
Data Index: 5049512 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.4329. Min Act: -0.1700
Data Index: 6276928 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.5267. Min Act: -0.1700
Data Index: 2916355 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.4642. Min Act: -0.1700
Data Index: 2450266 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.4642. Min Act: -0.1700
Data Index: 4026661 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.4642. Min Act: -0.1700
Data Index: 7708283 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.4017. Min Act: -0.1700
Data Index: 440989 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0892. Min Range: -7.0892
Max Act: 6.4329. Min Act: -0.1700
Data Index: 3794411 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #19