Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4008 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.6175. Min Act: -0.1700
Data Index: 7819904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.5563. Min Act: -0.1697
Data Index: 3073125 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.5651. Min Act: -0.1700
Data Index: 4852755 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.5476. Min Act: -0.1690
Data Index: 6667714 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.5125. Min Act: -0.1697
Data Index: 5064417 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.5125. Min Act: -0.1700
Data Index: 3991752 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.5125. Min Act: -0.1691
Data Index: 428177 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4950. Min Act: -0.1687
Data Index: 6667234 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4862. Min Act: -0.1691
Data Index: 4093870 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4862. Min Act: -0.1674
Data Index: 1770375 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4862. Min Act: -0.1694
Data Index: 291130 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4774. Min Act: -0.1697
Data Index: 7930270 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4774. Min Act: -0.1699
Data Index: 5482452 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4774. Min Act: -0.1691
Data Index: 6630150 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4774. Min Act: -0.1700
Data Index: 3922479 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4774. Min Act: -0.1700
Data Index: 7208568 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4598. Min Act: -0.1700
Data Index: 6976808 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4686. Min Act: -0.1700
Data Index: 7509324 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4686. Min Act: -0.1691
Data Index: 3113273 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6175. Min Range: -1.6175
Max Act: 1.4686. Min Act: -0.1696
Data Index: 3316812 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #19