Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 908 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.3217. Min Range: -8.3217
Max Act: 8.3217. Min Act: -0.1700
Data Index: 2100849 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3217. Min Range: -8.3217
Max Act: 8.1967. Min Act: -0.1700
Data Index: 6357399 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3217. Min Range: -8.3217
Max Act: 8.1342. Min Act: -0.1700
Data Index: 883003 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3217. Min Range: -8.3217
Max Act: 8.1342. Min Act: -0.1700
Data Index: 3009000 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3217. Min Range: -8.3217
Max Act: 8.1342. Min Act: -0.1700
Data Index: 8308349 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3217. Min Range: -8.3217
Max Act: 8.0717. Min Act: -0.1700
Data Index: 1555755 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3217. Min Range: -8.3217
Max Act: 8.0717. Min Act: -0.1700
Data Index: 4955185 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3217. Min Range: -8.3217
Max Act: 8.0717. Min Act: -0.1700
Data Index: 4385169 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3217. Min Range: -8.3217
Max Act: 8.0717. Min Act: -0.1700
Data Index: 6000633 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3217. Min Range: -8.3217
Max Act: 8.0092. Min Act: -0.1700
Data Index: 6617440 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3217. Min Range: -8.3217
Max Act: 8.0092. Min Act: -0.1700
Data Index: 8289782 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3217. Min Range: -8.3217
Max Act: 7.8842. Min Act: -0.1700
Data Index: 5876620 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3217. Min Range: -8.3217
Max Act: 7.9467. Min Act: -0.1700
Data Index: 3954334 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3217. Min Range: -8.3217
Max Act: 7.9467. Min Act: -0.1700
Data Index: 297007 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3217. Min Range: -8.3217
Max Act: 7.9467. Min Act: -0.1700
Data Index: 1228783 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3217. Min Range: -8.3217
Max Act: 7.8842. Min Act: -0.1700
Data Index: 2291998 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3217. Min Range: -8.3217
Max Act: 7.8842. Min Act: -0.1700
Data Index: 6758410 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3217. Min Range: -8.3217
Max Act: 7.8842. Min Act: -0.1700
Data Index: 5113681 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3217. Min Range: -8.3217
Max Act: 7.8842. Min Act: -0.1700
Data Index: 7838453 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3217. Min Range: -8.3217
Max Act: 7.8842. Min Act: -0.1700
Data Index: 3167971 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19