Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1350 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.7301. Min Act: -0.1700
Data Index: 6563596 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.6519. Min Act: -0.1700
Data Index: 1137946 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.6362. Min Act: -0.1700
Data Index: 6850103 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.6049. Min Act: -0.1700
Data Index: 522595 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5893. Min Act: -0.1700
Data Index: 4021069 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5580. Min Act: -0.1700
Data Index: 648191 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5580. Min Act: -0.1700
Data Index: 380197 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5580. Min Act: -0.1700
Data Index: 2274461 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5423. Min Act: -0.1700
Data Index: 118532 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5423. Min Act: -0.1700
Data Index: 1567136 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5423. Min Act: -0.1700
Data Index: 5277039 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5580. Min Act: -0.1700
Data Index: 6598247 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5267. Min Act: -0.1700
Data Index: 5049422 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5267. Min Act: -0.1700
Data Index: 946572 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5267. Min Act: -0.1700
Data Index: 3159257 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5110. Min Act: -0.1700
Data Index: 4316202 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5110. Min Act: -0.1700
Data Index: 296651 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5110. Min Act: -0.1700
Data Index: 2428384 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.4797. Min Act: -0.1700
Data Index: 233077 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7301. Min Range: -3.7301
Max Act: 3.5110. Min Act: -0.1700
Data Index: 1716135 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #19