Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2780 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.4480. Min Act: -0.1676
Data Index: 1170837 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.3991. Min Act: -0.1700
Data Index: 1433763 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.3501. Min Act: -0.1700
Data Index: 6329762 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.3337. Min Act: -0.1700
Data Index: 1170838 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2843. Min Act: -0.1700
Data Index: 6233967 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.3008. Min Act: -0.1700
Data Index: 5955852 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2843. Min Act: -0.1700
Data Index: 4581081 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2348. Min Act: -0.1699
Data Index: 1170836 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2348. Min Act: -0.1700
Data Index: 5633160 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2183. Min Act: -0.1700
Data Index: 2870788 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2183. Min Act: -0.1700
Data Index: 5349375 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2183. Min Act: -0.1700
Data Index: 6363437 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2183. Min Act: -0.1700
Data Index: 1546621 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2017. Min Act: -0.1700
Data Index: 8385742 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2183. Min Act: -0.1700
Data Index: 7244422 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2017. Min Act: -0.1700
Data Index: 5776256 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2017. Min Act: -0.1700
Data Index: 1563276 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2017. Min Act: -0.1700
Data Index: 2197556 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.1851. Min Act: -0.1700
Data Index: 1261518 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4480. Min Range: -2.4480
Max Act: 2.2017. Min Act: -0.1700
Data Index: 520732 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19