Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 974 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.5044. Min Act: -0.1700
Data Index: 6691674 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.5044. Min Act: -0.1700
Data Index: 1103879 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.3794. Min Act: -0.1700
Data Index: 6851401 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.3482. Min Act: -0.1700
Data Index: 2945977 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.3169. Min Act: -0.1700
Data Index: 1806144 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.2231. Min Act: -0.1700
Data Index: 378065 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.2231. Min Act: -0.1700
Data Index: 6102803 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1606. Min Act: -0.1700
Data Index: 8622005 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1919. Min Act: -0.1700
Data Index: 4239883 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1606. Min Act: -0.1700
Data Index: 8530015 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1606. Min Act: -0.1700
Data Index: 1109196 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1606. Min Act: -0.1700
Data Index: 3252322 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1606. Min Act: -0.1700
Data Index: 7905667 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1294. Min Act: -0.1700
Data Index: 1612370 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1294. Min Act: -0.1700
Data Index: 7973764 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.1294. Min Act: -0.1700
Data Index: 7076950 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0981. Min Act: -0.1700
Data Index: 1518536 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0981. Min Act: -0.1700
Data Index: 7921925 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0981. Min Act: -0.1700
Data Index: 5124406 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5044. Min Range: -4.5044
Max Act: 4.0981. Min Act: -0.1700
Data Index: 4488713 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19