Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.7967. Min Act: -0.1700
Data Index: 6240695 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.6717. Min Act: -0.1700
Data Index: 2141686 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.6717. Min Act: -0.1700
Data Index: 8782522 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.6092. Min Act: -0.1700
Data Index: 432561 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.6717. Min Act: -0.1700
Data Index: 6104932 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.5467. Min Act: -0.1700
Data Index: 7202133 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.6092. Min Act: -0.1700
Data Index: 5046950 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.4217. Min Act: -0.1700
Data Index: 5879992 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.4217. Min Act: -0.1700
Data Index: 6545796 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.4217. Min Act: -0.1700
Data Index: 1487976 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.4217. Min Act: -0.1700
Data Index: 5660900 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.4217. Min Act: -0.1700
Data Index: 5565230 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.3592. Min Act: -0.1700
Data Index: 5506917 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2967. Min Act: -0.1700
Data Index: 4841814 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2967. Min Act: -0.1700
Data Index: 5650282 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2967. Min Act: -0.1700
Data Index: 3356578 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2967. Min Act: -0.1700
Data Index: 3316756 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2342. Min Act: -0.1700
Data Index: 7268313 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2967. Min Act: -0.1700
Data Index: 7198084 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7967. Min Range: -8.7967
Max Act: 8.2967. Min Act: -0.1700
Data Index: 4098081 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19