Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3824 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.9420. Min Act: -0.1700
Data Index: 985225 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.9108. Min Act: -0.1700
Data Index: 8090480 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.8170. Min Act: -0.1700
Data Index: 5831223 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.8170. Min Act: -0.1700
Data Index: 5831222 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.8170. Min Act: -0.1700
Data Index: 4598408 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.7858. Min Act: -0.1700
Data Index: 7110671 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.8170. Min Act: -0.1700
Data Index: 423845 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.7545. Min Act: -0.1700
Data Index: 1212049 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.7545. Min Act: -0.1700
Data Index: 38031 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.7233. Min Act: -0.1700
Data Index: 6343972 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.7233. Min Act: -0.1700
Data Index: 3973385 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.6920. Min Act: -0.1700
Data Index: 8005977 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.6920. Min Act: -0.1700
Data Index: 4945384 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.6920. Min Act: -0.1700
Data Index: 8265294 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.6920. Min Act: -0.1700
Data Index: 7321900 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.6920. Min Act: -0.1700
Data Index: 420302 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.6920. Min Act: -0.1700
Data Index: 5119351 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.7233. Min Act: -0.1700
Data Index: 5210131 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.6608. Min Act: -0.1700
Data Index: 5199438 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9420. Min Range: -4.9420
Max Act: 4.6608. Min Act: -0.1700
Data Index: 5085741 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19