Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1609 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.7407. Min Act: -0.1700
Data Index: 612222 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.7320. Min Act: -0.1693
Data Index: 3750638 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.7234. Min Act: -0.1700
Data Index: 792851 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.7060. Min Act: -0.1700
Data Index: 8022183 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.7060. Min Act: -0.1700
Data Index: 318355 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.7147. Min Act: -0.1700
Data Index: 6615616 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.7060. Min Act: -0.1700
Data Index: 4336096 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.6974. Min Act: -0.1700
Data Index: 8009643 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.7060. Min Act: -0.1700
Data Index: 5847836 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.6974. Min Act: -0.1700
Data Index: 6452656 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.6626. Min Act: -0.1700
Data Index: 3267113 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.6800. Min Act: -0.1700
Data Index: 7101069 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.6800. Min Act: -0.1700
Data Index: 7463645 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.6800. Min Act: -0.1699
Data Index: 6883888 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.6800. Min Act: -0.1700
Data Index: 5753513 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.6713. Min Act: -0.1700
Data Index: 3026751 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.6713. Min Act: -0.1700
Data Index: 7001764 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.6713. Min Act: -0.1661
Data Index: 5928113 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.6800. Min Act: -0.1700
Data Index: 4242071 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7407. Min Range: -1.7407
Max Act: 1.6713. Min Act: -0.1700
Data Index: 4323496 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #19