Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 782 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1435. Min Range: -4.1435
Max Act: 4.0810. Min Act: -0.1700
Data Index: 4917839 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1435. Min Range: -4.1435
Max Act: 4.1435. Min Act: -0.1700
Data Index: 284081 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1435. Min Range: -4.1435
Max Act: 4.0810. Min Act: -0.1700
Data Index: 4467892 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1435. Min Range: -4.1435
Max Act: 4.0497. Min Act: -0.1700
Data Index: 7074816 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.9872. Min Act: -0.1700
Data Index: 4830259 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.9872. Min Act: -0.1700
Data Index: 5752466 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.9247. Min Act: -0.1700
Data Index: 5272445 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.9559. Min Act: -0.1700
Data Index: 3240292 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.9559. Min Act: -0.1700
Data Index: 3240294 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.9559. Min Act: -0.1700
Data Index: 1396699 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.9872. Min Act: -0.1700
Data Index: 2335901 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.9559. Min Act: -0.1700
Data Index: 2428590 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.9559. Min Act: -0.1700
Data Index: 8674172 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.9247. Min Act: -0.1700
Data Index: 8401471 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.8934. Min Act: -0.1700
Data Index: 7164755 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.8934. Min Act: -0.1700
Data Index: 4091564 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.9247. Min Act: -0.1700
Data Index: 6421352 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.8309. Min Act: -0.1700
Data Index: 4899672 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.8934. Min Act: -0.1700
Data Index: 1001904 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1435. Min Range: -4.1435
Max Act: 3.8934. Min Act: -0.1700
Data Index: 4927193 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19