Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 853 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.3739. Min Range: -6.3739
Max Act: 6.3427. Min Act: -0.1700
Data Index: 2767195 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3739. Min Range: -6.3739
Max Act: 6.3739. Min Act: -0.1700
Data Index: 8553340 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3739. Min Range: -6.3739
Max Act: 6.1864. Min Act: -0.1700
Data Index: 1845644 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3739. Min Range: -6.3739
Max Act: 6.0302. Min Act: -0.1700
Data Index: 2266430 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3739. Min Range: -6.3739
Max Act: 6.0302. Min Act: -0.1700
Data Index: 6404333 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.9677. Min Act: -0.1700
Data Index: 8122825 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.9364. Min Act: -0.1700
Data Index: 1565621 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.9364. Min Act: -0.1700
Data Index: 2429658 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.8427. Min Act: -0.1700
Data Index: 4459461 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.8739. Min Act: -0.1700
Data Index: 5570715 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.8739. Min Act: -0.1700
Data Index: 2143062 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.8427. Min Act: -0.1700
Data Index: 4476368 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.8114. Min Act: -0.1700
Data Index: 7551956 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.7802. Min Act: -0.1700
Data Index: 7658166 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.7489. Min Act: -0.1700
Data Index: 4476371 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.7489. Min Act: -0.1700
Data Index: 8027799 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.7489. Min Act: -0.1700
Data Index: 861127 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.7489. Min Act: -0.1700
Data Index: 7967584 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.7177. Min Act: -0.1700
Data Index: 7203114 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3739. Min Range: -6.3739
Max Act: 5.6864. Min Act: -0.1700
Data Index: 6019942 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19