Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3259 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.8240. Min Act: -0.1700
Data Index: 817929 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6990. Min Act: -0.1700
Data Index: 8770211 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6990. Min Act: -0.1700
Data Index: 2193132 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6677. Min Act: -0.1700
Data Index: 466925 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6365. Min Act: -0.1700
Data Index: 5303275 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6052. Min Act: -0.1700
Data Index: 7935981 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.6052. Min Act: -0.1700
Data Index: 3015896 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5740. Min Act: -0.1700
Data Index: 7885250 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5740. Min Act: -0.1700
Data Index: 1569090 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5740. Min Act: -0.1700
Data Index: 2332129 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4802. Min Act: -0.1700
Data Index: 3194678 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5115. Min Act: -0.1700
Data Index: 5879938 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5115. Min Act: -0.1700
Data Index: 1312059 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5115. Min Act: -0.1700
Data Index: 3999397 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.5115. Min Act: -0.1700
Data Index: 2910057 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4490. Min Act: -0.1700
Data Index: 4429867 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4490. Min Act: -0.1700
Data Index: 3111687 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4490. Min Act: -0.1700
Data Index: 3194682 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4177. Min Act: -0.1700
Data Index: 1995424 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8240. Min Range: -5.8240
Max Act: 5.4177. Min Act: -0.1700
Data Index: 440875 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19