Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 618 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.7133. Min Act: -0.1700
Data Index: 3685871 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.5571. Min Act: -0.1700
Data Index: 1964474 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4946. Min Act: -0.1700
Data Index: 1668836 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.5258. Min Act: -0.1700
Data Index: 2492646 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.5258. Min Act: -0.1700
Data Index: 936093 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4946. Min Act: -0.1700
Data Index: 204157 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4946. Min Act: -0.1700
Data Index: 1509974 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4946. Min Act: -0.1700
Data Index: 7712608 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4633. Min Act: -0.1700
Data Index: 6167804 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4633. Min Act: -0.1700
Data Index: 4459726 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4321. Min Act: -0.1700
Data Index: 3549897 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4008. Min Act: -0.1700
Data Index: 2670144 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.3696. Min Act: -0.1700
Data Index: 8417225 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4008. Min Act: -0.1700
Data Index: 3637303 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4008. Min Act: -0.1700
Data Index: 1720718 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4008. Min Act: -0.1700
Data Index: 5217238 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.3696. Min Act: -0.1700
Data Index: 2828153 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4008. Min Act: -0.1700
Data Index: 598795 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.4008. Min Act: -0.1700
Data Index: 6996815 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7133. Min Range: -5.7133
Max Act: 5.3696. Min Act: -0.1700
Data Index: 7146321 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #19