Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2392 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.5423. Min Act: -0.1700
Data Index: 6157272 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.5160. Min Act: -0.1695
Data Index: 4905727 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.5160. Min Act: -0.1700
Data Index: 7139093 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.5073. Min Act: -0.1698
Data Index: 6281703 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.5160. Min Act: -0.1700
Data Index: 2628236 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4985. Min Act: -0.1700
Data Index: 7592931 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4897. Min Act: -0.1692
Data Index: 6734918 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4897. Min Act: -0.1694
Data Index: 8255771 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4809. Min Act: -0.1700
Data Index: 5533329 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4809. Min Act: -0.1700
Data Index: 2327215 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4633. Min Act: -0.1700
Data Index: 5048109 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4545. Min Act: -0.1695
Data Index: 731720 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4633. Min Act: -0.1700
Data Index: 8234559 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4633. Min Act: -0.1695
Data Index: 8704870 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4369. Min Act: -0.1700
Data Index: 176232 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4457. Min Act: -0.1700
Data Index: 3320259 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4457. Min Act: -0.1673
Data Index: 404399 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4457. Min Act: -0.1700
Data Index: 4758192 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4545. Min Act: -0.1700
Data Index: 5284618 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5423. Min Range: -1.5423
Max Act: 1.4457. Min Act: -0.1700
Data Index: 4617902 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #19