Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1015 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.6766. Min Act: -0.1700
Data Index: 8571992 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.6446. Min Act: -0.1700
Data Index: 3005112 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.6285. Min Act: -0.1700
Data Index: 766338 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.5318. Min Act: -0.1700
Data Index: 4207020 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.5480. Min Act: -0.1700
Data Index: 4585767 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.5480. Min Act: -0.1700
Data Index: 8207694 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.5156. Min Act: -0.1700
Data Index: 8571989 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4994. Min Act: -0.1700
Data Index: 8781205 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4832. Min Act: -0.1700
Data Index: 6877065 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4832. Min Act: -0.1700
Data Index: 1725464 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4507. Min Act: -0.1700
Data Index: 2119939 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4670. Min Act: -0.1700
Data Index: 8525279 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4507. Min Act: -0.1700
Data Index: 1307235 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4670. Min Act: -0.1700
Data Index: 607914 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4507. Min Act: -0.1700
Data Index: 8571988 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4670. Min Act: -0.1700
Data Index: 1519277 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4507. Min Act: -0.1700
Data Index: 8356991 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4345. Min Act: -0.1700
Data Index: 2960618 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4507. Min Act: -0.1700
Data Index: 88446 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6766. Min Range: -2.6766
Max Act: 2.4345. Min Act: -0.1700
Data Index: 5063478 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #19